In [2]:
!pip install tensorflow
Collecting tensorflow
  Obtaining dependency information for tensorflow from https://files.pythonhosted.org/packages/ed/b6/62345568cd07de5d9254fcf64d7e44aacbb6abde11ea953b3cb320e58d19/tensorflow-2.17.0-cp311-cp311-win_amd64.whl.metadata
  Downloading tensorflow-2.17.0-cp311-cp311-win_amd64.whl.metadata (3.2 kB)
Collecting tensorflow-intel==2.17.0 (from tensorflow)
  Obtaining dependency information for tensorflow-intel==2.17.0 from https://files.pythonhosted.org/packages/66/03/5c447feceb72f5a38ac2aa79d306fa5b5772f982c2b480c1329c7e382900/tensorflow_intel-2.17.0-cp311-cp311-win_amd64.whl.metadata
  Downloading tensorflow_intel-2.17.0-cp311-cp311-win_amd64.whl.metadata (5.0 kB)
Collecting absl-py>=1.0.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for absl-py>=1.0.0 from https://files.pythonhosted.org/packages/a2/ad/e0d3c824784ff121c03cc031f944bc7e139a8f1870ffd2845cc2dd76f6c4/absl_py-2.1.0-py3-none-any.whl.metadata
  Downloading absl_py-2.1.0-py3-none-any.whl.metadata (2.3 kB)
Collecting astunparse>=1.6.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for astunparse>=1.6.0 from https://files.pythonhosted.org/packages/2b/03/13dde6512ad7b4557eb792fbcf0c653af6076b81e5941d36ec61f7ce6028/astunparse-1.6.3-py2.py3-none-any.whl.metadata
  Downloading astunparse-1.6.3-py2.py3-none-any.whl.metadata (4.4 kB)
Collecting flatbuffers>=24.3.25 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for flatbuffers>=24.3.25 from https://files.pythonhosted.org/packages/41/f0/7e988a019bc54b2dbd0ad4182ef2d53488bb02e58694cd79d61369e85900/flatbuffers-24.3.25-py2.py3-none-any.whl.metadata
  Downloading flatbuffers-24.3.25-py2.py3-none-any.whl.metadata (850 bytes)
Collecting gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 from https://files.pythonhosted.org/packages/a3/61/8001b38461d751cd1a0c3a6ae84346796a5758123f3ed97a1b121dfbf4f3/gast-0.6.0-py3-none-any.whl.metadata
  Downloading gast-0.6.0-py3-none-any.whl.metadata (1.3 kB)
Collecting google-pasta>=0.1.1 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for google-pasta>=0.1.1 from https://files.pythonhosted.org/packages/a3/de/c648ef6835192e6e2cc03f40b19eeda4382c49b5bafb43d88b931c4c74ac/google_pasta-0.2.0-py3-none-any.whl.metadata
  Downloading google_pasta-0.2.0-py3-none-any.whl.metadata (814 bytes)
Collecting h5py>=3.10.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for h5py>=3.10.0 from https://files.pythonhosted.org/packages/d8/5e/b7b83cfe60504cc4d24746aed04353af7ea8ec104e597e5ae71b8d0390cb/h5py-3.11.0-cp311-cp311-win_amd64.whl.metadata
  Downloading h5py-3.11.0-cp311-cp311-win_amd64.whl.metadata (2.5 kB)
Collecting libclang>=13.0.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for libclang>=13.0.0 from https://files.pythonhosted.org/packages/0b/2d/3f480b1e1d31eb3d6de5e3ef641954e5c67430d5ac93b7fa7e07589576c7/libclang-18.1.1-py2.py3-none-win_amd64.whl.metadata
  Downloading libclang-18.1.1-py2.py3-none-win_amd64.whl.metadata (5.3 kB)
Collecting ml-dtypes<0.5.0,>=0.3.1 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for ml-dtypes<0.5.0,>=0.3.1 from https://files.pythonhosted.org/packages/f0/36/290745178e5776f7416818abc1334c1b19afb93c7c87fd1bef3cc99f84ca/ml_dtypes-0.4.0-cp311-cp311-win_amd64.whl.metadata
  Downloading ml_dtypes-0.4.0-cp311-cp311-win_amd64.whl.metadata (20 kB)
Collecting opt-einsum>=2.3.2 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for opt-einsum>=2.3.2 from https://files.pythonhosted.org/packages/bc/19/404708a7e54ad2798907210462fd950c3442ea51acc8790f3da48d2bee8b/opt_einsum-3.3.0-py3-none-any.whl.metadata
  Downloading opt_einsum-3.3.0-py3-none-any.whl.metadata (6.5 kB)
Requirement already satisfied: packaging in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (23.0)
Collecting protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 from https://files.pythonhosted.org/packages/0c/d4/589d673ada9c4c62d5f155218d7ff7ac796efb9c6af95b0bd29d438ae16e/protobuf-4.25.4-cp310-abi3-win_amd64.whl.metadata
  Downloading protobuf-4.25.4-cp310-abi3-win_amd64.whl.metadata (541 bytes)
Requirement already satisfied: requests<3,>=2.21.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (2.31.0)
Requirement already satisfied: setuptools in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (68.0.0)
Requirement already satisfied: six>=1.12.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (1.16.0)
Collecting termcolor>=1.1.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for termcolor>=1.1.0 from https://files.pythonhosted.org/packages/d9/5f/8c716e47b3a50cbd7c146f45881e11d9414def768b7cd9c5e6650ec2a80a/termcolor-2.4.0-py3-none-any.whl.metadata
  Downloading termcolor-2.4.0-py3-none-any.whl.metadata (6.1 kB)
Requirement already satisfied: typing-extensions>=3.6.6 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (4.7.1)
Requirement already satisfied: wrapt>=1.11.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (1.14.1)
Collecting grpcio<2.0,>=1.24.3 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for grpcio<2.0,>=1.24.3 from https://files.pythonhosted.org/packages/74/12/257ab1687ab913aa39330092a9816014bfcf108557f05869a4d40e01ece1/grpcio-1.65.4-cp311-cp311-win_amd64.whl.metadata
  Downloading grpcio-1.65.4-cp311-cp311-win_amd64.whl.metadata (3.4 kB)
Collecting tensorboard<2.18,>=2.17 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for tensorboard<2.18,>=2.17 from https://files.pythonhosted.org/packages/0a/32/2e8545fb0592f33e3aca5951e8b01008b76d61b440658cbdc37b4eaebf0b/tensorboard-2.17.0-py3-none-any.whl.metadata
  Downloading tensorboard-2.17.0-py3-none-any.whl.metadata (1.6 kB)
Collecting keras>=3.2.0 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for keras>=3.2.0 from https://files.pythonhosted.org/packages/a3/a4/101f0f3c0b057ce150af0e8493ab7fc10b98b066b7bd81ab01e96038a268/keras-3.5.0-py3-none-any.whl.metadata
  Downloading keras-3.5.0-py3-none-any.whl.metadata (5.8 kB)
Collecting tensorflow-io-gcs-filesystem>=0.23.1 (from tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for tensorflow-io-gcs-filesystem>=0.23.1 from https://files.pythonhosted.org/packages/ac/4e/9566a313927be582ca99455a9523a097c7888fc819695bdc08415432b202/tensorflow_io_gcs_filesystem-0.31.0-cp311-cp311-win_amd64.whl.metadata
  Downloading tensorflow_io_gcs_filesystem-0.31.0-cp311-cp311-win_amd64.whl.metadata (14 kB)
Requirement already satisfied: numpy<2.0.0,>=1.23.5 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow) (1.24.3)
Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\programdata\anaconda3\lib\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.17.0->tensorflow) (0.38.4)
Collecting rich (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for rich from https://files.pythonhosted.org/packages/87/67/a37f6214d0e9fe57f6ae54b2956d550ca8365857f42a1ce0392bb21d9410/rich-13.7.1-py3-none-any.whl.metadata
  Downloading rich-13.7.1-py3-none-any.whl.metadata (18 kB)
Collecting namex (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for namex from https://files.pythonhosted.org/packages/73/59/7854fbfb59f8ae35483ce93493708be5942ebb6328cd85b3a609df629736/namex-0.0.8-py3-none-any.whl.metadata
  Downloading namex-0.0.8-py3-none-any.whl.metadata (246 bytes)
Collecting optree (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for optree from https://files.pythonhosted.org/packages/12/26/ce14a11c328bfcf29341da42342cc48e4d65fb44e4e559c9e4036a88b750/optree-0.12.1-cp311-cp311-win_amd64.whl.metadata
  Downloading optree-0.12.1-cp311-cp311-win_amd64.whl.metadata (48 kB)
     ---------------------------------------- 0.0/48.7 kB ? eta -:--:--
     ---------------------------------------- 48.7/48.7 kB 2.4 MB/s eta 0:00:00
Requirement already satisfied: charset-normalizer<4,>=2 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow) (2023.7.22)
Requirement already satisfied: markdown>=2.6.8 in c:\programdata\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow) (3.4.1)
Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow)
  Obtaining dependency information for tensorboard-data-server<0.8.0,>=0.7.0 from https://files.pythonhosted.org/packages/7a/13/e503968fefabd4c6b2650af21e110aa8466fe21432cd7c43a84577a89438/tensorboard_data_server-0.7.2-py3-none-any.whl.metadata
  Downloading tensorboard_data_server-0.7.2-py3-none-any.whl.metadata (1.1 kB)
Requirement already satisfied: werkzeug>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow) (2.2.3)
Requirement already satisfied: MarkupSafe>=2.1.1 in c:\programdata\anaconda3\lib\site-packages (from werkzeug>=1.0.1->tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow) (2.1.1)
Requirement already satisfied: markdown-it-py>=2.2.0 in c:\programdata\anaconda3\lib\site-packages (from rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (2.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\programdata\anaconda3\lib\site-packages (from rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (2.15.1)
Requirement already satisfied: mdurl~=0.1 in c:\programdata\anaconda3\lib\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (0.1.0)
Downloading tensorflow-2.17.0-cp311-cp311-win_amd64.whl (2.0 kB)
Downloading tensorflow_intel-2.17.0-cp311-cp311-win_amd64.whl (385.0 MB)
   ---------------------------------------- 0.0/385.0 MB ? eta -:--:--
   ---------------------------------------- 2.0/385.0 MB 64.4 MB/s eta 0:00:06
    --------------------------------------- 6.4/385.0 MB 81.5 MB/s eta 0:00:05
   - ------------------------------------- 12.0/385.0 MB 108.8 MB/s eta 0:00:04
   - ------------------------------------- 17.4/385.0 MB 110.0 MB/s eta 0:00:04
   -- ------------------------------------ 22.7/385.0 MB 110.0 MB/s eta 0:00:04
   -- ------------------------------------ 27.3/385.0 MB 108.8 MB/s eta 0:00:04
   --- ------------------------------------ 31.9/385.0 MB 93.9 MB/s eta 0:00:04
   --- ----------------------------------- 36.5/385.0 MB 110.0 MB/s eta 0:00:04
   ---- ---------------------------------- 41.1/385.0 MB 108.8 MB/s eta 0:00:04
   ---- ---------------------------------- 45.9/385.0 MB 108.8 MB/s eta 0:00:04
   ----- --------------------------------- 50.6/385.0 MB 108.8 MB/s eta 0:00:04
   ----- --------------------------------- 55.3/385.0 MB 108.8 MB/s eta 0:00:04
   ------ -------------------------------- 60.1/385.0 MB 108.8 MB/s eta 0:00:03
   ------ -------------------------------- 64.9/385.0 MB 108.8 MB/s eta 0:00:03
   ------- ------------------------------- 69.8/385.0 MB 110.0 MB/s eta 0:00:03
   ------- ------------------------------- 74.7/385.0 MB 108.8 MB/s eta 0:00:03
   -------- ------------------------------ 79.5/385.0 MB 108.8 MB/s eta 0:00:03
   -------- ------------------------------ 83.8/385.0 MB 110.0 MB/s eta 0:00:03
   --------- ----------------------------- 89.5/385.0 MB 110.0 MB/s eta 0:00:03
   --------- ----------------------------- 94.6/385.0 MB 108.8 MB/s eta 0:00:03
   ---------- ---------------------------- 99.8/385.0 MB 108.8 MB/s eta 0:00:03
   ---------- --------------------------- 104.9/385.0 MB 108.8 MB/s eta 0:00:03
   ---------- --------------------------- 110.3/385.0 MB 108.8 MB/s eta 0:00:03
   ----------- -------------------------- 115.6/385.0 MB 108.8 MB/s eta 0:00:03
   ----------- -------------------------- 121.1/385.0 MB 131.2 MB/s eta 0:00:03
   ------------ ------------------------- 126.5/385.0 MB 110.0 MB/s eta 0:00:03
   ------------- ------------------------ 131.7/385.0 MB 131.2 MB/s eta 0:00:02
   ------------- ------------------------ 137.1/385.0 MB 129.5 MB/s eta 0:00:02
   -------------- ----------------------- 142.6/385.0 MB 131.2 MB/s eta 0:00:02
   -------------- ----------------------- 147.9/385.0 MB 131.2 MB/s eta 0:00:02
   --------------- ---------------------- 153.2/385.0 MB 131.2 MB/s eta 0:00:02
   --------------- ---------------------- 158.5/385.0 MB 108.8 MB/s eta 0:00:03
   ---------------- --------------------- 163.8/385.0 MB 108.8 MB/s eta 0:00:03
   ---------------- --------------------- 169.1/385.0 MB 108.8 MB/s eta 0:00:02
   ----------------- -------------------- 174.5/385.0 MB 108.8 MB/s eta 0:00:02
   ----------------- -------------------- 179.8/385.0 MB 108.8 MB/s eta 0:00:02
   ------------------ ------------------- 185.1/385.0 MB 131.2 MB/s eta 0:00:02
   ------------------ ------------------- 190.4/385.0 MB 131.2 MB/s eta 0:00:02
   ------------------- ------------------ 195.8/385.0 MB 129.5 MB/s eta 0:00:02
   ------------------- ------------------ 201.2/385.0 MB 110.0 MB/s eta 0:00:02
   -------------------- ----------------- 206.6/385.0 MB 110.0 MB/s eta 0:00:02
   -------------------- ----------------- 212.0/385.0 MB 108.8 MB/s eta 0:00:02
   --------------------- ---------------- 217.3/385.0 MB 108.8 MB/s eta 0:00:02
   --------------------- ---------------- 222.8/385.0 MB 108.8 MB/s eta 0:00:02
   ---------------------- --------------- 228.3/385.0 MB 108.8 MB/s eta 0:00:02
   ----------------------- -------------- 233.5/385.0 MB 108.8 MB/s eta 0:00:02
   ----------------------- -------------- 237.0/385.0 MB 108.8 MB/s eta 0:00:02
   ----------------------- -------------- 242.4/385.0 MB 108.8 MB/s eta 0:00:02
   ------------------------ -------------- 243.3/385.0 MB 93.9 MB/s eta 0:00:02
   ------------------------- ------------- 246.9/385.0 MB 72.6 MB/s eta 0:00:02
   ------------------------- ------------- 252.2/385.0 MB 73.1 MB/s eta 0:00:02
   ------------------------- ------------ 257.6/385.0 MB 110.0 MB/s eta 0:00:02
   ------------------------- ------------ 263.1/385.0 MB 108.8 MB/s eta 0:00:02
   -------------------------- ----------- 268.4/385.0 MB 108.8 MB/s eta 0:00:02
   --------------------------- ---------- 273.7/385.0 MB 108.8 MB/s eta 0:00:02
   --------------------------- ---------- 279.1/385.0 MB 108.8 MB/s eta 0:00:01
   ---------------------------- --------- 284.5/385.0 MB 108.8 MB/s eta 0:00:01
   ---------------------------- --------- 289.6/385.0 MB 131.2 MB/s eta 0:00:01
   ----------------------------- -------- 294.5/385.0 MB 108.8 MB/s eta 0:00:01
   ----------------------------- -------- 299.3/385.0 MB 108.8 MB/s eta 0:00:01
   ----------------------------- -------- 303.9/385.0 MB 108.8 MB/s eta 0:00:01
   ------------------------------ ------- 308.5/385.0 MB 110.0 MB/s eta 0:00:01
   ------------------------------- ------- 312.1/385.0 MB 93.9 MB/s eta 0:00:01
   ------------------------------- ------- 315.4/385.0 MB 81.8 MB/s eta 0:00:01
   -------------------------------- ------ 318.8/385.0 MB 72.6 MB/s eta 0:00:01
   -------------------------------- ------ 322.3/385.0 MB 72.6 MB/s eta 0:00:01
   --------------------------------- ----- 325.8/385.0 MB 72.6 MB/s eta 0:00:01
   --------------------------------- ----- 329.2/385.0 MB 81.8 MB/s eta 0:00:01
   --------------------------------- ----- 332.9/385.0 MB 81.8 MB/s eta 0:00:01
   ---------------------------------- ---- 336.6/385.0 MB 81.8 MB/s eta 0:00:01
   ---------------------------------- ---- 340.2/385.0 MB 81.8 MB/s eta 0:00:01
   ---------------------------------- ---- 343.9/385.0 MB 81.8 MB/s eta 0:00:01
   ----------------------------------- --- 347.6/385.0 MB 81.8 MB/s eta 0:00:01
   ----------------------------------- --- 351.3/385.0 MB 81.8 MB/s eta 0:00:01
   ----------------------------------- --- 355.2/385.0 MB 81.8 MB/s eta 0:00:01
   ------------------------------------ -- 359.1/385.0 MB 81.8 MB/s eta 0:00:01
   ------------------------------------ -- 363.0/385.0 MB 81.8 MB/s eta 0:00:01
   ------------------------------------- - 366.8/385.0 MB 93.9 MB/s eta 0:00:01
   ------------------------------------- - 370.9/385.0 MB 93.9 MB/s eta 0:00:01
   ------------------------------------- - 375.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  379.1/385.0 MB 93.0 MB/s eta 0:00:01
   --------------------------------------  383.4/385.0 MB 93.0 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------  385.0/385.0 MB 93.9 MB/s eta 0:00:01
   --------------------------------------- 385.0/385.0 MB 11.9 MB/s eta 0:00:00
Downloading absl_py-2.1.0-py3-none-any.whl (133 kB)
   ---------------------------------------- 0.0/133.7 kB ? eta -:--:--
   ---------------------------------------- 133.7/133.7 kB 4.0 MB/s eta 0:00:00
Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Downloading flatbuffers-24.3.25-py2.py3-none-any.whl (26 kB)
Downloading gast-0.6.0-py3-none-any.whl (21 kB)
Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)
   ---------------------------------------- 0.0/57.5 kB ? eta -:--:--
   ---------------------------------------- 57.5/57.5 kB ? eta 0:00:00
Downloading grpcio-1.65.4-cp311-cp311-win_amd64.whl (4.1 MB)
   ---------------------------------------- 0.0/4.1 MB ? eta -:--:--
   -------------------------------- ------- 3.4/4.1 MB 105.3 MB/s eta 0:00:01
   ---------------------------------------- 4.1/4.1 MB 65.6 MB/s eta 0:00:00
Downloading h5py-3.11.0-cp311-cp311-win_amd64.whl (3.0 MB)
   ---------------------------------------- 0.0/3.0 MB ? eta -:--:--
   ---------------------------------------  3.0/3.0 MB 95.5 MB/s eta 0:00:01
   ---------------------------------------- 3.0/3.0 MB 47.9 MB/s eta 0:00:00
Downloading keras-3.5.0-py3-none-any.whl (1.1 MB)
   ---------------------------------------- 0.0/1.1 MB ? eta -:--:--
   ---------------------------------------- 1.1/1.1 MB 71.0 MB/s eta 0:00:00
Downloading libclang-18.1.1-py2.py3-none-win_amd64.whl (26.4 MB)
   ---------------------------------------- 0.0/26.4 MB ? eta -:--:--
   ----- ---------------------------------- 3.6/26.4 MB 115.3 MB/s eta 0:00:01
   ----------- ---------------------------- 7.9/26.4 MB 101.3 MB/s eta 0:00:01
   ------------------ --------------------- 12.4/26.4 MB 93.0 MB/s eta 0:00:01
   ------------------------ --------------- 16.4/26.4 MB 93.9 MB/s eta 0:00:01
   -------------------------------- ------- 21.3/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------  25.9/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------  26.4/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------  26.4/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------  26.4/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------  26.4/26.4 MB 93.9 MB/s eta 0:00:01
   ---------------------------------------- 26.4/26.4 MB 34.4 MB/s eta 0:00:00
Downloading ml_dtypes-0.4.0-cp311-cp311-win_amd64.whl (126 kB)
   ---------------------------------------- 0.0/126.8 kB ? eta -:--:--
   ---------------------------------------- 126.8/126.8 kB 3.8 MB/s eta 0:00:00
Downloading opt_einsum-3.3.0-py3-none-any.whl (65 kB)
   ---------------------------------------- 0.0/65.5 kB ? eta -:--:--
   ---------------------------------------- 65.5/65.5 kB ? eta 0:00:00
Downloading protobuf-4.25.4-cp310-abi3-win_amd64.whl (413 kB)
   ---------------------------------------- 0.0/413.4 kB ? eta -:--:--
   --------------------------------------- 413.4/413.4 kB 25.2 MB/s eta 0:00:00
Downloading tensorboard-2.17.0-py3-none-any.whl (5.5 MB)
   ---------------------------------------- 0.0/5.5 MB ? eta -:--:--
   ------------------------------------ --- 5.0/5.5 MB 155.5 MB/s eta 0:00:01
   ---------------------------------------- 5.5/5.5 MB 69.5 MB/s eta 0:00:00
Downloading tensorflow_io_gcs_filesystem-0.31.0-cp311-cp311-win_amd64.whl (1.5 MB)
   ---------------------------------------- 0.0/1.5 MB ? eta -:--:--
   ---------------------------------------- 1.5/1.5 MB 31.4 MB/s eta 0:00:00
Downloading termcolor-2.4.0-py3-none-any.whl (7.7 kB)
Downloading tensorboard_data_server-0.7.2-py3-none-any.whl (2.4 kB)
Downloading namex-0.0.8-py3-none-any.whl (5.8 kB)
Downloading optree-0.12.1-cp311-cp311-win_amd64.whl (268 kB)
   ---------------------------------------- 0.0/268.5 kB ? eta -:--:--
   --------------------------------------- 268.5/268.5 kB 16.1 MB/s eta 0:00:00
Downloading rich-13.7.1-py3-none-any.whl (240 kB)
   ---------------------------------------- 0.0/240.7 kB ? eta -:--:--
   ---------------------------------------- 240.7/240.7 kB ? eta 0:00:00
Installing collected packages: namex, libclang, flatbuffers, termcolor, tensorflow-io-gcs-filesystem, tensorboard-data-server, protobuf, optree, opt-einsum, ml-dtypes, h5py, grpcio, google-pasta, gast, astunparse, absl-py, tensorboard, rich, keras, tensorflow-intel, tensorflow
  Attempting uninstall: h5py
    Found existing installation: h5py 3.7.0
    Uninstalling h5py-3.7.0:
      Successfully uninstalled h5py-3.7.0
Successfully installed absl-py-2.1.0 astunparse-1.6.3 flatbuffers-24.3.25 gast-0.6.0 google-pasta-0.2.0 grpcio-1.65.4 h5py-3.11.0 keras-3.5.0 libclang-18.1.1 ml-dtypes-0.4.0 namex-0.0.8 opt-einsum-3.3.0 optree-0.12.1 protobuf-4.25.4 rich-13.7.1 tensorboard-2.17.0 tensorboard-data-server-0.7.2 tensorflow-2.17.0 tensorflow-intel-2.17.0 tensorflow-io-gcs-filesystem-0.31.0 termcolor-2.4.0
In [4]:
!pip install tensorflow-recommenders
Collecting tensorflow-recommenders
  Obtaining dependency information for tensorflow-recommenders from https://files.pythonhosted.org/packages/d3/91/7f9977f26bc0c94269d3f157710e9f1a112d1af23d4588285d846228ce3c/tensorflow_recommenders-0.7.3-py3-none-any.whl.metadata
  Downloading tensorflow_recommenders-0.7.3-py3-none-any.whl.metadata (4.6 kB)
Requirement already satisfied: absl-py>=0.1.6 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-recommenders) (2.1.0)
Requirement already satisfied: tensorflow>=2.9.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-recommenders) (2.17.0)
Requirement already satisfied: tensorflow-intel==2.17.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow>=2.9.0->tensorflow-recommenders) (2.17.0)
Requirement already satisfied: astunparse>=1.6.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.6.3)
Requirement already satisfied: flatbuffers>=24.3.25 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (24.3.25)
Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.6.0)
Requirement already satisfied: google-pasta>=0.1.1 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.2.0)
Requirement already satisfied: h5py>=3.10.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (3.11.0)
Requirement already satisfied: libclang>=13.0.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (18.1.1)
Requirement already satisfied: ml-dtypes<0.5.0,>=0.3.1 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.4.0)
Requirement already satisfied: opt-einsum>=2.3.2 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (3.3.0)
Requirement already satisfied: packaging in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (23.0)
Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (4.25.4)
Requirement already satisfied: requests<3,>=2.21.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.31.0)
Requirement already satisfied: setuptools in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (68.0.0)
Requirement already satisfied: six>=1.12.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.16.0)
Requirement already satisfied: termcolor>=1.1.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.4.0)
Requirement already satisfied: typing-extensions>=3.6.6 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (4.7.1)
Requirement already satisfied: wrapt>=1.11.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.14.1)
Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.65.4)
Requirement already satisfied: tensorboard<2.18,>=2.17 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.17.0)
Requirement already satisfied: keras>=3.2.0 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (3.5.0)
Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.31.0)
Requirement already satisfied: numpy<2.0.0,>=1.23.5 in c:\programdata\anaconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.24.3)
Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\programdata\anaconda3\lib\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.38.4)
Requirement already satisfied: rich in c:\programdata\anaconda3\lib\site-packages (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (13.7.1)
Requirement already satisfied: namex in c:\programdata\anaconda3\lib\site-packages (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.0.8)
Requirement already satisfied: optree in c:\programdata\anaconda3\lib\site-packages (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.12.1)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\programdata\anaconda3\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2023.7.22)
Requirement already satisfied: markdown>=2.6.8 in c:\programdata\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (3.4.1)
Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\programdata\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.7.2)
Requirement already satisfied: werkzeug>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.2.3)
Requirement already satisfied: MarkupSafe>=2.1.1 in c:\programdata\anaconda3\lib\site-packages (from werkzeug>=1.0.1->tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.1.1)
Requirement already satisfied: markdown-it-py>=2.2.0 in c:\programdata\anaconda3\lib\site-packages (from rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\programdata\anaconda3\lib\site-packages (from rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (2.15.1)
Requirement already satisfied: mdurl~=0.1 in c:\programdata\anaconda3\lib\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow>=2.9.0->tensorflow-recommenders) (0.1.0)
Downloading tensorflow_recommenders-0.7.3-py3-none-any.whl (96 kB)
   ---------------------------------------- 0.0/96.2 kB ? eta -:--:--
   ---------------------------------------- 96.2/96.2 kB 5.4 MB/s eta 0:00:00
Installing collected packages: tensorflow-recommenders
Successfully installed tensorflow-recommenders-0.7.3
In [5]:
import pandas as pd
import numpy as np
import re 
import matplotlib.pyplot as plt
import plotly.express as px
import pandas as pd
import tensorflow as tf
import tensorflow as tf
from tensorflow.keras.layers import StringLookup, Embedding, LayerNormalization
import tensorflow_recommenders as tfrs
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from sklearn.metrics import confusion_matrix
In [6]:
df = pd.read_csv("C:\\Users\\sa2259\\OneDrive - University of Sussex\\Desktop\\project final\\Recommendation System\\Recommendation_data_retail.csv")
In [7]:
df.head()
Out[7]:
Trx_id Timestamp Member_id Item_id Item_name Item_subclass Item_subdepartment Itm_qty Item_price Total_price
0 173131329 2022-11-21 00:02:36.017 5136784 1260 Tomato /kg tomato fresh vegetable 1 10.665 10.665
1 173131329 2022-11-21 00:02:36.017 5136784 50668 Lamb Weston Crunchy Seasoned Twisters 2.5 kg spiced fries-onion frozen food 1 26.550 26.550
2 173131329 2022-11-21 00:02:36.017 5136784 2116 Orange Juice /Kg banana african fresh fruits 1 24.273 24.273
3 173131329 2022-11-21 00:02:36.017 5136784 73732 Pinar Shredded Mozzarella Cheese 500g shredded mozzarela cheese cheese 2 37.800 75.600
4 173131329 2022-11-21 00:02:36.017 5136784 298472 Radwa Fried Chicken 900g chicken drumsticks frozen food 1 28.575 28.575
In [8]:
# Assuming unique_items_df has already been created
unique_items_df = df[['Item_id', 'Item_name']].drop_duplicates().reset_index(drop=True)

# Step 1: Group by 'Item_name' and count the number of unique 'Item_id's
item_name_counts = unique_items_df.groupby('Item_name')['Item_id'].nunique().reset_index(name='unique_item_id_count')

# Step 2: Filter the 'Item_name's that have more than one unique 'Item_id'
item_names_with_multiple_ids = item_name_counts[item_name_counts['unique_item_id_count'] > 1]

# To get the item names as a list or dataframe
item_names_list = item_names_with_multiple_ids['Item_name'].tolist()
item_names_df = item_names_with_multiple_ids[['Item_name']]

# If you want to get the original rows from unique_items_df for these Item_name's
filtered_df = unique_items_df[unique_items_df['Item_name'].isin(item_names_list)]
In [9]:
item_names_with_multiple_ids
Out[9]:
Item_name unique_item_id_count
669 1:16 Friction Construction Truck With Light & ... 2
30009 Abu Bint Golden Parboiled Chopstick Rice 10kg 2
30613 Al Manseb Natural Honey 500 g 2
31005 Alali Vanilla Powder 12X20g 2
31520 American Garden Iodized Table Salt 26 Oz 2
... ... ...
46805 Whiskas Cat Food 85 g 2
46808 Whiskas Dry Cat Food 1.2Kg 2
46810 Whiskas Dry Cat Food 480g 2
46814 Whiskas Wet Cat Food 12*70g 2
47002 Zucchini (Tray) 2

109 rows × 2 columns

We realize that 109 item_names are tagged with multiple Item_Ids, which could be due to system tagging based on barcode or anything of that sort. So for better embeddings in later stages we'll drop Item_name column and consider Item_Id to be unique Identifier for Items.

In [10]:
# Assuming item_names_with_multiple_ids is already defined
# Plot histogram
plt.figure(figsize=(10, 6))
plt.hist(item_names_with_multiple_ids['unique_item_id_count'], bins=range(1, item_names_with_multiple_ids['unique_item_id_count'].max() + 2), edgecolor='black')
plt.xlabel('Number of Unique Item IDs')
plt.ylabel('Frequency')
plt.title('Histogram of Item Names with Multiple Unique Item IDs')
plt.grid(True)
plt.show()
In [11]:
df1 = df.copy()
In [12]:
df1.drop(columns='Item_name',inplace=True)
In [13]:
df1.head()
Out[13]:
Trx_id Timestamp Member_id Item_id Item_subclass Item_subdepartment Itm_qty Item_price Total_price
0 173131329 2022-11-21 00:02:36.017 5136784 1260 tomato fresh vegetable 1 10.665 10.665
1 173131329 2022-11-21 00:02:36.017 5136784 50668 spiced fries-onion frozen food 1 26.550 26.550
2 173131329 2022-11-21 00:02:36.017 5136784 2116 banana african fresh fruits 1 24.273 24.273
3 173131329 2022-11-21 00:02:36.017 5136784 73732 shredded mozzarela cheese cheese 2 37.800 75.600
4 173131329 2022-11-21 00:02:36.017 5136784 298472 chicken drumsticks frozen food 1 28.575 28.575
In [14]:
df2 = df1[df1['Item_price'] >= 0]
In [15]:
#Converting Timestamp column to date-time format for time-intelligence Operation.
df2['Timestamp'] = pd.to_datetime(df2['Timestamp'])
C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\2581994025.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df2['Timestamp'] = pd.to_datetime(df2['Timestamp'])
In [16]:
#Adjusting From UTC to Regional Time
df2['Timestamp'] = df2['Timestamp'] + pd.Timedelta(hours=3)
C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\467794843.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df2['Timestamp'] = df2['Timestamp'] + pd.Timedelta(hours=3)

We are going to segregate Fresh and Non-fresh subdepartmens to better identify the choice taken by members, As most frequent buyers will have Fresh items dominantly in their top items while other items being present they will be overshadowed compared to these.

In [17]:
df2.head()
Out[17]:
Trx_id Timestamp Member_id Item_id Item_subclass Item_subdepartment Itm_qty Item_price Total_price
0 173131329 2022-11-21 03:02:36.017 5136784 1260 tomato fresh vegetable 1 10.665 10.665
1 173131329 2022-11-21 03:02:36.017 5136784 50668 spiced fries-onion frozen food 1 26.550 26.550
2 173131329 2022-11-21 03:02:36.017 5136784 2116 banana african fresh fruits 1 24.273 24.273
3 173131329 2022-11-21 03:02:36.017 5136784 73732 shredded mozzarela cheese cheese 2 37.800 75.600
4 173131329 2022-11-21 03:02:36.017 5136784 298472 chicken drumsticks frozen food 1 28.575 28.575
In [18]:
# Extract time of day and create corresponding columns
def get_time_of_day(hour):
    if 5 <= hour < 8:
        return 'early_morning'
    elif 8 <= hour < 12:
        return 'morning'
    elif 12 <= hour < 17:
        return 'noon'
    elif 17 <= hour < 20:
        return 'evening'
    elif 20 <= hour < 24:
        return 'night'
    else:
        return 'late_night'

df2['hour'] = df2['Timestamp'].dt.hour
df2['time_of_day'] = df2['hour'].apply(get_time_of_day)
C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3479529261.py:16: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df2['hour'] = df2['Timestamp'].dt.hour
C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3479529261.py:17: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df2['time_of_day'] = df2['hour'].apply(get_time_of_day)
In [19]:
df2.head()
Out[19]:
Trx_id Timestamp Member_id Item_id Item_subclass Item_subdepartment Itm_qty Item_price Total_price hour time_of_day
0 173131329 2022-11-21 03:02:36.017 5136784 1260 tomato fresh vegetable 1 10.665 10.665 3 late_night
1 173131329 2022-11-21 03:02:36.017 5136784 50668 spiced fries-onion frozen food 1 26.550 26.550 3 late_night
2 173131329 2022-11-21 03:02:36.017 5136784 2116 banana african fresh fruits 1 24.273 24.273 3 late_night
3 173131329 2022-11-21 03:02:36.017 5136784 73732 shredded mozzarela cheese cheese 2 37.800 75.600 3 late_night
4 173131329 2022-11-21 03:02:36.017 5136784 298472 chicken drumsticks frozen food 1 28.575 28.575 3 late_night
In [20]:
agg_by_time = df2.groupby(
    ['Member_id', 'Item_id', 'Item_subclass', 'Item_subdepartment', 'time_of_day']
)[['Itm_qty', 'Item_price', 'Total_price']].sum().reset_index()
In [21]:
agg_by_time
Out[21]:
Member_id Item_id Item_subclass Item_subdepartment time_of_day Itm_qty Item_price Total_price
0 4 1164 banana fresh fruits evening 2 12.447 12.447
1 4 1996 zero vat zero vat items evening 1 180.000 180.000
2 4 2192 laban full fat laban & labneh noon 1 1.800 1.800
3 4 3200 fresh milk full fat milk evening 1 5.400 5.400
4 4 4276 dates dates (supplier) late_night 1 20.250 20.250
... ... ... ... ... ... ... ... ...
4510843 10723344 957260 camel milk milk late_night 1 11.250 11.250
4510844 10723414 88 f bread bakery late_night 4 4.140 16.560
4510845 10723414 49800 fresh juice normal fresh juice late_night 1 6.750 6.750
4510846 10723414 74436 pickle & olive -weight pickle & olive late_night 1 5.076 5.076
4510847 10723414 452304 fresh juice normal fresh juice late_night 1 6.750 6.750

4510848 rows × 8 columns

In [22]:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Set style for seaborn
sns.set(style="whitegrid")
In [23]:
plt.figure(figsize=(12, 6))

# Plot histogram for 'Itm_qty'
plt.subplot(1, 3, 1)
sns.histplot(agg_by_time['Itm_qty'], bins=20, kde=True)
plt.title('Distribution of Item Quantity')

# Plot histogram for 'Item_price'
plt.subplot(1, 3, 2)
sns.histplot(agg_by_time['Item_price'], bins=20, kde=True)
plt.title('Distribution of Item Price')

# Plot histogram for 'Total_price'
plt.subplot(1, 3, 3)
sns.histplot(agg_by_time['Total_price'], bins=20, kde=True)
plt.title('Distribution of Total Price')

plt.tight_layout()
plt.show()
In [24]:
plt.figure(figsize=(10, 8))
correlation_matrix = agg_by_time[['Itm_qty', 'Item_price', 'Total_price']].corr()
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f')
plt.title('Correlation Matrix')
plt.show()
In [25]:
# Aggregate total prices by time of day
total_price_by_time = df2.groupby('time_of_day')['Total_price'].sum().reset_index()

# Create the bar chart
fig = px.bar(total_price_by_time, x='time_of_day', y='Total_price',
             title='Total Sales Distribution by Time of Day',
             labels={'Total_price': 'Total Price', 'time_of_day': 'Time of Day'},
             color='time_of_day',
             color_discrete_sequence=px.colors.sequential.Viridis)

# Customize the layout
fig.update_traces(texttemplate='%{y}', textposition='inside')
fig.update_layout(showlegend=False)

# Display the bar chart
fig.show()
In [26]:
# Aggregate total prices by time of day
total_price_by_time = df2.groupby('time_of_day')['Total_price'].sum().reset_index()

# Create the bar chart
fig = px.bar(total_price_by_time, x='time_of_day', y='Total_price',
             title='Total Sales Distribution by Time of Day',
             labels={'Total_price': 'Total Price', 'time_of_day': 'Time of Day'},
             color='time_of_day',
             color_discrete_sequence=px.colors.sequential.Viridis)

# Customize the layout with data labels formatted to 2 decimal places and larger font size
fig.update_traces(
    texttemplate='%{y:.2f}',  # Format labels to 2 decimal places
    textposition='inside',
    textfont=dict(size=14, color='White')  # Increase font size and set color to black
)
fig.update_layout(showlegend=False)

# Display the bar chart
fig.show()
In [27]:
import pandas as pd
import plotly.express as px

# Load your dataset
# df2 = pd.read_csv('your_data.csv') # Uncomment and adjust as needed

# Group by 'Item_subdepartment' and calculate total sales
sales_per_item_subdepartment = df2.groupby('Item_subdepartment')['Total_price'].sum().reset_index()

# Create a bar plot using Plotly
fig = px.bar(
    sales_per_item_subdepartment,
    x='Item_subdepartment',
    y='Total_price',
    color='Total_price',
    color_continuous_scale='viridis',
    title='Total Sales by Item Subdepartment'
)

# Customize the layout
fig.update_layout(
    xaxis_title='Item Subdepartment',
    yaxis_title='Total Price',
    xaxis_tickangle=-45
)

# Show the plot
fig.show()
In [28]:
import pandas as pd
import plotly.express as px

# Load your dataset
# df2 = pd.read_csv('your_data.csv') # Uncomment and adjust as needed

# Group by 'Item_subdepartment' and calculate total sales
sales_per_item_subdepartment = df2.groupby('Item_subdepartment')['Total_price'].sum().reset_index()

# Create a bar plot using Plotly
fig = px.bar(
    sales_per_item_subdepartment,
    x='Item_subdepartment',
    y='Total_price',
    color='Total_price',
    color_continuous_scale='viridis',
    title='Total Sales by Item Subdepartment',
    text='Total_price'  # Add data labels
)

# Customize the layout with data labels
fig.update_traces(
    texttemplate='%{text:.2f}',  # Format labels to 2 decimal places
    textposition='outside',      # Position labels outside the bars
    textfont=dict(size=12, color='black')  # Set font size and color
)

# Customize the layout
fig.update_layout(
    xaxis_title='Item Subdepartment',
    yaxis_title='Total Price',
    xaxis_tickangle=-45
)

# Show the plot
fig.show()
In [29]:
import pandas as pd
import plotly.express as px

# Load your dataset
# df2 = pd.read_csv('your_data.csv') # Uncomment and adjust as needed

# Group by 'Item_subdepartment' and calculate total sales
sales_per_item_subclass = df2.groupby('Item_subclass')['Total_price'].sum().reset_index()

# Create a bar plot using Plotly
fig = px.bar(
    sales_per_item_subclass,
    x='Item_subclass',
    y='Total_price',
    color='Total_price',
    color_continuous_scale='viridis',
    title='Total Sales by Item Subclass' 
)

# Customize the layout
fig.update_layout(
    xaxis_title='Item Subclass',
    yaxis_title='Total Price',
    xaxis_tickangle=-45
)

# Show the plot
fig.show()
In [30]:
# Plot boxplots for 'Itm_qty', 'Item_price', and 'Total_price' to visualize outliers
plt.figure(figsize=(15, 5))

# Boxplot for 'Itm_qty'
plt.subplot(1, 3, 1)
sns.boxplot(data=df2, y='Itm_qty', palette='coolwarm')
plt.title('Boxplot of Item Quantity')

# Boxplot for 'Item_price'
plt.subplot(1, 3, 2)
sns.boxplot(data=df2, y='Item_price', palette='coolwarm')
plt.title('Boxplot of Item Price')

# Boxplot for 'Total_price'
plt.subplot(1, 3, 3)
sns.boxplot(data=df2, y='Total_price', palette='coolwarm')
plt.title('Boxplot of Total Price')

plt.tight_layout()
plt.show()
In [31]:
import pandas as pd

# Assuming df2 is your DataFrame

# 1. Get the top 100 products by total sales
top_100_products = df2.groupby('Item_id')['Total_price'].sum().reset_index()
top_100_products = top_100_products.sort_values(by='Total_price', ascending=False).head(100)

# 2. Get the top 10 subclasses by total sales
top_10_subclasses = df2.groupby('Item_subclass')['Total_price'].sum().reset_index()
top_10_subclasses = top_10_subclasses.sort_values(by='Total_price', ascending=False).head(10)

# 3. Get the top 10 subdepartments by total sales
top_10_subdepartments = df2.groupby('Item_subdepartment')['Total_price'].sum().reset_index()
top_10_subdepartments = top_10_subdepartments.sort_values(by='Total_price', ascending=False).head(10)

# Display the results
print("Top 100 Products by Sales:")
print(top_100_products)

print("\nTop 10 Subclasses by Sales:")
print(top_10_subclasses)

print("\nTop 10 Subdepartments by Sales:")
print(top_10_subdepartments)
Top 100 Products by Sales:
       Item_id  Total_price
81        1264   870351.939
424       3504   757484.055
5           28   622401.849
1429      9856   557529.939
148       1560   536595.804
...        ...          ...
3600     26812   110926.638
124       1452   109881.774
36785   730812   109510.875
10770    86520   109500.345
4622     37136   109489.041

[100 rows x 2 columns]

Top 10 Subclasses by Sales:
                Item_subclass  Total_price
580             fresh chicken  7535658.186
579                fresh beef  2856952.584
900             mineral water  2609127.405
237            cheese -weight  2554750.197
1332  supplier finished goods  2107845.837
212         carbonated drinks  2088466.236
864                  managish  1928468.745
529                   f cakes  1887850.359
584                fresh fish  1648223.739
599              fresh mutton  1595273.967

Top 10 Subdepartments by Sales:
            Item_subdepartment   Total_price
49               confectionary  1.007549e+07
103                frozen food  8.421967e+06
138         juices & beverages  7.721683e+06
95               fresh chicken  7.535658e+06
33                      cheese  6.260865e+06
102            fresh vegetable  6.180319e+06
97                fresh fruits  5.174071e+06
15   bakery f-goods (in-house)  3.875085e+06
121              hot beverages  3.189698e+06
13                      bakery  3.180744e+06
In [32]:
import pandas as pd
import plotly.express as px

# Assuming df2 is your DataFrame and has columns 'Member_id' and 'Total_price'

# 1. Calculate total revenue per member
revenue_per_member = df2.groupby('Member_id')['Total_price'].sum().reset_index()

# 2. Define revenue bands (buckets)
bins = [0, 100, 500, 1000, 5000, 10000, float('inf')]  # Define your revenue bands
labels = ['0-100', '101-500', '501-1000', '1001-5000', '5001-10000', '10000+']  # Labels for each bucket

# Create a new column 'Revenue_Band' in the DataFrame
revenue_per_member['Revenue_Band'] = pd.cut(revenue_per_member['Total_price'], bins=bins, labels=labels)

# 3. Aggregate counts for each revenue band
revenue_band_counts = revenue_per_member['Revenue_Band'].value_counts().reset_index()
revenue_band_counts.columns = ['Revenue_Band', 'Count']

# Sort by descending order of count
revenue_band_counts = revenue_band_counts.sort_values(by='Count', ascending=False)

# 4. Plot a histogram of revenue bands
fig = px.bar(
    revenue_band_counts,
    x='Revenue_Band',
    y='Count',
    title='Histogram of Revenue Bands for Members',
    labels={'Revenue_Band': 'Revenue Band', 'Count': 'Number of Members'},
    color='Revenue_Band',
    color_discrete_sequence=px.colors.sequential.Viridis
)

# Customize the layout
fig.update_layout(
    xaxis_title='Revenue Band',
    yaxis_title='Number of Members',
    xaxis_tickangle=-45
)

# Show the plot
fig.show()
In [ ]:
 
In [33]:
pattern = r'\bfresh\b'
# Find unique 'Product_subclass' values matching the pattern (case-insensitive)
df2[df2['Item_subdepartment'].str.contains(pattern, case=False, regex=True)]
Out[33]:
Trx_id Timestamp Member_id Item_id Item_subclass Item_subdepartment Itm_qty Item_price Total_price hour time_of_day
0 173131329 2022-11-21 03:02:36.017 5136784 1260 tomato fresh vegetable 1 10.665 10.665 3 late_night
2 173131329 2022-11-21 03:02:36.017 5136784 2116 banana african fresh fruits 1 24.273 24.273 3 late_night
8 173131329 2022-11-21 03:02:36.017 5136784 3860 carrot fresh vegetable 1 1.926 1.926 3 late_night
15 173131344 2022-11-21 03:03:08.410 294748 1264 mixed leaves fresh vegetable 1 1.350 1.350 3 late_night
23 173131329 2022-11-21 03:02:36.017 5136784 44 onion african fresh vegetable 1 5.418 5.418 3 late_night
... ... ... ... ... ... ... ... ... ... ... ...
5500281 262036500 2023-07-21 02:20:50.880 2442722 156 potato fresh vegetable 1 12.465 12.465 2 late_night
5500282 262036500 2023-07-21 02:20:50.880 2442722 2804 fresh juice normal fresh juice 1 14.355 14.355 2 late_night
5500285 262036500 2023-07-21 02:20:50.880 2442722 41428 grapes fresh fruits 2 10.710 21.420 2 late_night
5500287 262036500 2023-07-21 02:20:50.880 2442722 151976 local cucumber fresh vegetable 1 8.955 8.955 2 late_night
5500288 262036500 2023-07-21 02:20:50.880 2442722 811944 fresh juice normal fresh juice 3 5.400 16.200 2 late_night

1311747 rows × 11 columns

In [34]:
current_date = df2['Timestamp'].max()
# Compute additional features
member_features_df = df2.groupby('Member_id').agg(
    Total_spend=('Total_price', 'sum'),
    Total_trx=('Trx_id', 'nunique'),
    Total_item=('Item_id', 'count'),
    Total_unique_items=('Item_id','nunique'),
    Total_unique_subclasses=('Item_subclass','nunique'),
    Total_unique_subdepartments=('Item_subdepartment','nunique'),
    Min_spend=('Total_price', 'min'),
    Max_spend=('Total_price','max'),
    days_since_last_purchase=('Timestamp', lambda x: (current_date - x.max()).days),
    days_since_first_purchase=('Timestamp', lambda x: (current_date - x.min()).days),
).reset_index()
member_features_df['spend_per_trx'] = member_features_df['Total_spend'] / member_features_df['Total_trx']
member_features_df['Items_per_trx'] = np.ceil(member_features_df['Total_item'] / member_features_df['Total_trx'])
member_features_df['Unique_items_per_trx'] = np.ceil(member_features_df['Total_unique_items'] / member_features_df['Total_trx'])

periods = [7, 15, 60, 90]

# Most Frequently Purchased Products - FRESH (Top 5)
pattern_fresh = r'\bfresh\b'
def get_top_fresh_products_for_periods(df, periods, pattern_fresh):
    # Calculate the maximum timestamp for each member
    max_timestamp = df.groupby('Member_id')['Timestamp'].max().reset_index()
    max_timestamp.columns = ['Member_id', 'Max_Timestamp']

    # Merge the max_timestamp DataFrame with the original df to filter data
    df_with_max = pd.merge(df, max_timestamp, on='Member_id')

    # Initialize a list to store results for each period
    results = []

    for days in periods:
        # Calculate the start date for the period relative to each member's maximum timestamp
        df_with_max['Start_Date'] = df_with_max['Max_Timestamp'] - pd.Timedelta(days=days)

        # Filter to include only the data for the specified period
        filtered_data = df_with_max[(df_with_max['Timestamp'] >= df_with_max['Start_Date']) &
                                     (df_with_max['Timestamp'] <= df_with_max['Max_Timestamp'])]

        # Find most frequently purchased fresh products
        product_freq_fresh = filtered_data[filtered_data['Item_subdepartment'].str.contains(pattern_fresh, case=False, regex=True)]
        product_freq_fresh = product_freq_fresh.groupby(['Member_id', 'Item_id']).size().reset_index(name='counts')
        product_freq_fresh['rank'] = product_freq_fresh.groupby('Member_id')['counts'].rank(method='first', ascending=False)
        
        # Get the top products based on rank
        top_products = product_freq_fresh[product_freq_fresh['rank'] <= 5]
        
        # Pivot table to get top products for each member
        top_products_pivot = top_products.pivot_table(
            index='Member_id',
            columns='rank',
            values='Item_id',
            aggfunc=lambda x: ', '.join(map(str, x))  # Aggregate product IDs as comma-separated strings
        ).reset_index()
        
        # Rename columns
        top_products_pivot.columns = [
            'Member_id'
        ] + [f'top_{int(col)}_{days}_day_fresh_product' for col in top_products_pivot.columns if col != 'Member_id']
        
        # Append the result to the list
        results.append(top_products_pivot)

    # Merge all results on 'Member_id'
    combined_results = results[0]
    for result in results[1:]:
        combined_results = pd.merge(combined_results, result, on='Member_id', how='outer')

    # Ensure no duplicate 'Member_id' columns
    combined_results = combined_results.loc[:, ~combined_results.columns.duplicated()]

    return combined_results

# Most Frequently Purchased Products - NON-FRESH (Top 5)
def get_top_non_fresh_products_for_periods(df, periods, pattern_fresh):
    # Calculate the maximum timestamp for each member
    max_timestamp = df.groupby('Member_id')['Timestamp'].max().reset_index()
    max_timestamp.columns = ['Member_id', 'Max_Timestamp']

    # Merge the max_timestamp DataFrame with the original df to filter data
    df_with_max = pd.merge(df, max_timestamp, on='Member_id')

    # Initialize a list to store results for each period
    results = []

    for days in periods:
        # Calculate the start date for the period relative to each member's maximum timestamp
        df_with_max['Start_Date'] = df_with_max['Max_Timestamp'] - pd.Timedelta(days=days)

        # Filter to include only the data for the specified period
        filtered_data = df_with_max[(df_with_max['Timestamp'] >= df_with_max['Start_Date']) &
                                     (df_with_max['Timestamp'] <= df_with_max['Max_Timestamp'])]
    
        # Find most frequently purchased non-fresh products
        product_freq_non_fresh = filtered_data[~filtered_data['Item_subdepartment'].str.contains(pattern_fresh, case=False, regex=True)]
        product_freq_non_fresh = product_freq_non_fresh.groupby(['Member_id', 'Item_id']).size().reset_index(name='counts')
        product_freq_non_fresh['rank'] = product_freq_non_fresh.groupby('Member_id')['counts'].rank(method='first', ascending=False)
        
        # Get the top products based on rank
        top_products = product_freq_non_fresh[product_freq_non_fresh['rank'] <= 5]
        
        # Pivot table to get top products for each member
        top_products_pivot = top_products.pivot_table(
            index='Member_id',
            columns='rank',
            values='Item_id',
            aggfunc=lambda x: ', '.join(map(str, x))  # Aggregate product IDs as comma-separated strings
        ).reset_index()
        
        # Rename columns
        top_products_pivot.columns = [
            'Member_id'
        ] + [f'top_{int(col)}_{days}_day_non_fresh_product' for col in top_products_pivot.columns if col != 'Member_id']
        
        # Append the result to the list
        results.append(top_products_pivot)

    # Merge all results on 'Member_id'
    combined_results = results[0]
    for result in results[1:]:
        combined_results = pd.merge(combined_results, result, on='Member_id', how='outer')

    # Ensure no duplicate 'Member_id' columns
    combined_results = combined_results.loc[:, ~combined_results.columns.duplicated()]

    return combined_results

# Combine all features

top_5_products_fresh_pivot = get_top_fresh_products_for_periods(df2, periods, pattern_fresh)
member_features_df = member_features_df.merge(top_5_products_fresh_pivot, on='Member_id', how='left')
top_5_products_non_fresh_pivot = get_top_non_fresh_products_for_periods(df2, periods, pattern_fresh)
member_features_df = member_features_df.merge(top_5_products_non_fresh_pivot, on='Member_id', how='left')
In [35]:
# Compute additional features
item_features = df2.groupby('Item_id').agg(
    total_purchases=('Item_id', 'count'),
    total_spend=('Total_price', 'sum'),
    total_Itm_qty_purchased=('Itm_qty', 'sum')
).reset_index()

item_features.head()
periods = [7, 15, 60, 90]
Max_timestamp_all = df2['Timestamp'].max()


results = []

def rename_columns(df, period):
    columns = {}
    for col in df.columns:
        if col not in ['Item_id', 'Item_name', 'Item_subclass', 'Item_subdepartment']:
            columns[col] = f"{col}_{period}_days"
    df.rename(columns=columns, inplace=True)
    return df

for days in periods:
    # Calculate the start date for the period relative to each member's maximum timestamp
    df2['Start_Date'] = Max_timestamp_all - pd.Timedelta(days=days)

    # Filter to include only the data for the specified period
    filtered_data = df2[(df2['Timestamp'] >= df2['Start_Date']) &
                             (df2['Timestamp'] <= Max_timestamp_all)]

    # Find most frequently purchased fresh products
    Trx_count_items = filtered_data.groupby('Item_id')['Trx_id'].count().reset_index()
    Trx_count_items.columns = ['Item_id', 'Trx_count']  # Rename column for clarity

    item_sales = filtered_data.groupby(['Item_id', 'Item_subclass', 'Item_subdepartment'])[['Total_price','Itm_qty']].sum().reset_index()

    # Merge item_sales with Trx_count_items on 'Item_id'
    item_sales = item_sales.merge(Trx_count_items, on='Item_id', how='outer')

    # Rename columns with appropriate suffix
    item_sales = rename_columns(item_sales, days)

    # Append the result to the list
    results.append(item_sales)

# Merge all period dataframes into one dataframe
final_df = results[0]
for i in range(1, len(results)):
    final_df = final_df.merge(results[i], on=['Item_id', 'Item_subclass', 'Item_subdepartment'], how='outer')

# Fill NaN values with 0 if necessary
final_df.fillna(0, inplace=True)
C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3092105094.py:25: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3092105094.py:25: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3092105094.py:25: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\sa2259\AppData\Local\Temp\ipykernel_32820\3092105094.py:25: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

In [36]:
pd.set_option('display.max_columns',None)
final_df.head()
Out[36]:
Item_id Item_subclass Item_subdepartment Total_price_7_days Itm_qty_7_days Trx_count_7_days Total_price_15_days Itm_qty_15_days Trx_count_15_days Total_price_60_days Itm_qty_60_days Trx_count_60_days Total_price_90_days Itm_qty_90_days Trx_count_90_days
0 16 bar chocolates confectionary 13.275 3.0 2.0 21.240 6.0 3.0 162.315 37.0 21.0 291.915 75 46
1 20 fresh milk full fat milk 3808.800 220.0 151.0 6950.952 422.0 330.0 22402.602 1411.0 1219.0 34131.645 2183 1920
2 24 mineral water juices & beverages 7661.142 233.0 79.0 11367.702 442.0 173.0 28899.576 1792.0 717.0 43365.285 2838 1201
3 28 zam zam water juices & beverages 14407.407 872.0 327.0 32636.610 1917.0 680.0 121929.507 7527.0 2663.0 190673.649 11794 4141
4 32 mineral water juices & beverages 757.026 71.0 51.0 2714.328 275.0 154.0 11356.659 1044.0 509.0 14225.760 1351 664
In [37]:
Item_features_df = final_df.copy()
In [38]:
member_features_df.head()
Out[38]:
Member_id Total_spend Total_trx Total_item Total_unique_items Total_unique_subclasses Total_unique_subdepartments Min_spend Max_spend days_since_last_purchase days_since_first_purchase spend_per_trx Items_per_trx Unique_items_per_trx top_1_7_day_fresh_product top_2_7_day_fresh_product top_3_7_day_fresh_product top_4_7_day_fresh_product top_5_7_day_fresh_product top_1_15_day_fresh_product top_2_15_day_fresh_product top_3_15_day_fresh_product top_4_15_day_fresh_product top_5_15_day_fresh_product top_1_60_day_fresh_product top_2_60_day_fresh_product top_3_60_day_fresh_product top_4_60_day_fresh_product top_5_60_day_fresh_product top_1_90_day_fresh_product top_2_90_day_fresh_product top_3_90_day_fresh_product top_4_90_day_fresh_product top_5_90_day_fresh_product top_1_7_day_non_fresh_product top_2_7_day_non_fresh_product top_3_7_day_non_fresh_product top_4_7_day_non_fresh_product top_5_7_day_non_fresh_product top_1_15_day_non_fresh_product top_2_15_day_non_fresh_product top_3_15_day_non_fresh_product top_4_15_day_non_fresh_product top_5_15_day_non_fresh_product top_1_60_day_non_fresh_product top_2_60_day_non_fresh_product top_3_60_day_non_fresh_product top_4_60_day_non_fresh_product top_5_60_day_non_fresh_product top_1_90_day_non_fresh_product top_2_90_day_non_fresh_product top_3_90_day_non_fresh_product top_4_90_day_non_fresh_product top_5_90_day_non_fresh_product
0 4 1168.092 18 40 30 22 17 1.80 305.100 38 225 64.894000 3.0 2.0 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 1164 NaN NaN NaN NaN 1164 59128 70912 NaN NaN 767476 NaN NaN NaN NaN 767476 NaN NaN NaN NaN 3200 8748 22420 36444 44468 48848 1996 3200 8748 22420
1 6 1153.674 138 184 61 36 21 0.00 55.755 0 241 8.359957 2.0 1.0 NaN NaN NaN NaN NaN 156 48012 NaN NaN NaN 48012 156 1260 1264 2120 48012 156 44 1260 1264 1352 65428 66348 66460 66476 1352 65428 293556 2508 65436 1352 65436 68276 1356 1424 1352 65436 68276 1356 1424
2 12 8002.494 571 969 218 101 41 0.00 272.880 0 241 14.014876 2.0 1.0 44 176 1260 1264 2316 44 176 1260 1264 2316 44 176 1260 1264 2316 44 176 1260 1264 2316 1352 65436 86780 2624 65452 1352 65436 65452 2624 1424 1352 65436 65452 1424 1500 1352 65436 65452 1424 1500
3 14 985.077 32 92 69 49 26 0.00 46.755 20 237 30.783656 3.0 3.0 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 8764 12356 14468 67116 88740 8764 12356 14468 67116 88740 1356 NaN NaN NaN NaN 1356 NaN NaN NaN NaN 1356 8408 10196 16176 30340 1356 66448 1500 3428 8408
4 18 1080.333 18 37 25 17 10 1.35 445.500 3 233 60.018500 3.0 2.0 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 1504 NaN NaN NaN NaN 1352 2492 NaN NaN NaN 1352 2492 NaN NaN NaN 1352 2492 12780 51584 1356 1352 2492 1356 12780 51584
In [39]:
member_features_df = member_features_df.sort_values(by='Total_trx', ascending=False).head(1000)
In [40]:
member_features_df.fillna('NA',inplace=True)
Item_features_df.fillna('NA',inplace=True)
In [41]:
#Checking for nulls in both datasets.
print(f'Members_dataset:\n{member_features_df.isna().sum().sum()}\n')
print(f'Items_dataset:\n{Item_features_df.isna().sum().sum()}')
Members_dataset:
0

Items_dataset:
0
In [42]:
numerical_columns_members = np.array(member_features_df.columns[1:14])
# Get columns from index 58 onward
categorical_columns_from_58 = member_features_df.columns[14:]

# Get column 0
categorical_column_0 = member_features_df.columns[0]

# Combine both lists of columns
categorical_columns_members = np.concatenate(([categorical_column_0], categorical_columns_from_58))
In [43]:
categorical_columns_items = np.array(Item_features_df.columns[:3])
numerical_columns_items = np.array(Item_features_df.columns[3:])
In [44]:
# Define categorical and numerical features
categorical_features = {
    "members": categorical_columns_members,  # Example user features
    "items": categorical_columns_items  # Example item features
}

numerical_features = {
    "members": numerical_columns_members,  # Example user numerical features
    "items": numerical_columns_items  # Example item numerical features
}
In [45]:
# Create dictionary of unique features
unique_features_members_categorical = {}
unique_features_members_numerical = {}
unique_features_items_categorical = {}
unique_features_items_numerical = {}

# Helper function to convert values to strings
def convert_to_strings(values):
    return [str(value) for value in values]

def convert_to_float(values):
    return [float(value) for value in values]

# Extract unique values for member features
for feature in categorical_features["members"]:
    unique_values = member_features_df[feature].unique().tolist()
    unique_features_members_categorical[feature] = convert_to_strings(unique_values)

for feature in numerical_features["members"]:
    unique_values = member_features_df[feature].unique().tolist()
    unique_features_members_numerical[feature] = convert_to_float(unique_values)

# Extract unique values for item features
for feature in categorical_features["items"]:
    unique_values = Item_features_df[feature].unique().tolist()
    unique_features_items_categorical[feature] = convert_to_strings(unique_values)

for feature in numerical_features["items"]:
    unique_values = Item_features_df[feature].unique().tolist()
    unique_features_items_numerical[feature] = convert_to_float(unique_values)


# Convert dictionaries of unique features to tensors
unique_features_members_categorical_tf = {
    feature_name: tf.constant(vocabulary) for feature_name, vocabulary in unique_features_members_categorical.items()
}

unique_features_members_numerical_tf = {
    feature_name: tf.constant(values) for feature_name, values in unique_features_members_numerical.items()
}

unique_features_items_categorical_tf = {
    feature_name: tf.constant(vocabulary) for feature_name, vocabulary in unique_features_items_categorical.items()
}

unique_features_items_numerical_tf = {
    feature_name: tf.constant(values) for feature_name, values in unique_features_items_numerical.items()
}

Unique_member_ids_tf = tf.constant(unique_features_members_categorical['Member_id'])
Unique_Item_ids_tf = tf.constant(unique_features_items_categorical['Item_id'])
In [46]:
# Compute correlation matrix
correlation_matrix = member_features_df[numerical_columns_members].corr()

# Plot heatmap
plt.figure(figsize=(12, 10))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=.5)
plt.title('Correlation Matrix of Numerical Features')
plt.show()
In [47]:
# Compute correlation matrix
correlation_matrix = Item_features_df[numerical_columns_items].corr()

# Plot heatmap
plt.figure(figsize=(12, 10))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=.5)
plt.title('Correlation Matrix of Numerical Features')
plt.show()
In [48]:
# Initialize the combined dictionary
unique_features_members_combined = {}

# Process categorical features
for feature in categorical_features["members"]:
    unique_values = member_features_df[feature].unique().tolist()
    unique_features_members_combined[feature] = convert_to_strings(unique_values)

# Process numerical features
for feature in numerical_features["members"]:
    unique_values = member_features_df[feature].unique().tolist()
    unique_features_members_combined[feature] = convert_to_float(unique_values)
    
# Initialize the combined dictionary
unique_features_items_combined = {}

# Process categorical features
for feature in categorical_features["items"]:
    unique_values = Item_features_df[feature].unique().tolist()
    unique_features_items_combined[feature] = convert_to_strings(unique_values)

# Process numerical features
for feature in numerical_features["items"]:
    unique_values = Item_features_df[feature].unique().tolist()
    unique_features_items_combined[feature] = convert_to_float(unique_values)
    
member_features = {feature_name: tf.constant(values) for feature_name, values in unique_features_members_combined.items()}
item_features = {feature_name: tf.constant(values) for feature_name, values in unique_features_items_combined.items()}
In [49]:
import tensorflow as tf

class MemberModel(tf.keras.Model):
    def __init__(self, unique_member_ids, unique_features_categorical, unique_features_numerical, embedding_dim=32):
        super().__init__()
        self.embedding_dim = embedding_dim

        # Initialize the embedding layers dictionary
        self.embedding_layers = {}
        
        # Initialize normalization layers
        self.normalization_layers = {}

        # Initialize the Member_id lookup and embedding layer
        self.member_lookup = tf.keras.layers.StringLookup(vocabulary=unique_member_ids, mask_token=None, oov_token=None)
        self.member_embedding_layer = tf.keras.layers.Embedding(input_dim=self.member_lookup.vocabulary_size(), output_dim=embedding_dim)

        # Create embedding layers for other categorical features
        for feature_name, vocabulary in unique_features_categorical.items():
            if feature_name != 'Member_id':
                lookup = tf.keras.layers.StringLookup(vocabulary=vocabulary, mask_token=None, oov_token=None)
                vocab_size = lookup.vocabulary_size()
                embedding = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim)
                self.embedding_layers[feature_name] = (lookup, embedding)

        # Create normalization layers for numerical features
        for feature_name in unique_features_numerical:
            normalization_layer = tf.keras.layers.LayerNormalization(axis=-1, epsilon=1e-6)
            self.normalization_layers[feature_name] = normalization_layer

    def call(self, member_features):
        # Extract member_id and convert to embeddings
        member_id = member_features['Member_id']
        member_id_indices = self.member_lookup(member_id)
        member_embeddings = self.member_embedding_layer(member_id_indices)
        print(f"Shape of member_embeddings: {member_embeddings.shape}")

        # Prepare list for concatenation
        concatenated_features = [member_embeddings]

        # Process categorical features
        for feature_name, feature_values in member_features.items():
            if feature_name != 'Member_id':
                if feature_name in self.embedding_layers:
                    lookup, embedding = self.embedding_layers[feature_name]
                    feature_indices = lookup(feature_values)
                    feature_embeddings = embedding(feature_indices)
                    print(f"Shape of {feature_name} feature_embeddings (before padding): {feature_embeddings.shape}")

                    # Pad if needed to match batch size of member_embeddings
                    if feature_embeddings.shape[0] < member_embeddings.shape[0]:
                        padding_size = member_embeddings.shape[0] - feature_embeddings.shape[0]
                        feature_embeddings = tf.pad(feature_embeddings, [[0, padding_size], [0, 0]], constant_values=0)
                        print(f"Shape of {feature_name} feature_embeddings (after padding): {feature_embeddings.shape}")
                    
                    concatenated_features.append(feature_embeddings)

        # Process numerical features
        for feature_name, feature_values in member_features.items():
            if feature_name in self.normalization_layers:
                normalization_layer = self.normalization_layers[feature_name]
                normalized_values = normalization_layer(tf.expand_dims(feature_values, axis=0))
                normalized_values = tf.squeeze(normalized_values, axis=0)
                print(f"Shape of {feature_name} normalized_values (before padding): {normalized_values.shape}")

                # Pad if needed to match batch size
                if normalized_values.shape[0] < member_embeddings.shape[0]:
                    padding_size = member_embeddings.shape[0] - normalized_values.shape[0]
                    normalized_values = tf.pad(normalized_values, [[0, padding_size]], constant_values=0)
                    print(f"Shape of {feature_name} normalized_values (after padding): {normalized_values.shape}")
                
                concatenated_features.append(tf.expand_dims(normalized_values, axis=-1))

        # Concatenate all tensors along the last axis
        final_concatenated_tensor = tf.concat(concatenated_features, axis=-1)
        print(f"Shape of final_concatenated_tensor: {final_concatenated_tensor.shape}")

        return final_concatenated_tensor
In [50]:
member_model = MemberModel(
    unique_member_ids=Unique_member_ids_tf,
    unique_features_categorical=unique_features_members_categorical_tf,
    unique_features_numerical=unique_features_members_numerical_tf,
    embedding_dim=3
)
In [51]:
output_member_embedding = member_model(member_features)
Shape of member_embeddings: (1000, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (before padding): (140, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (before padding): (160, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (before padding): (150, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (before padding): (152, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (before padding): (143, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (before padding): (168, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (before padding): (169, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (before padding): (166, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (before padding): (154, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (before padding): (147, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (before padding): (177, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (before padding): (185, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (before padding): (136, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (before padding): (163, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (before padding): (182, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (before padding): (180, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (before padding): (402, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (before padding): (531, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (before padding): (561, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (before padding): (583, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (before padding): (401, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (before padding): (523, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (before padding): (560, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (before padding): (602, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (before padding): (366, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (before padding): (457, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (before padding): (515, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (before padding): (541, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (before padding): (585, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (before padding): (352, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (before padding): (432, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (before padding): (495, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (before padding): (535, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (before padding): (558, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of Total_spend normalized_values (before padding): (999,)
Shape of Total_spend normalized_values (after padding): (1000,)
Shape of Total_trx normalized_values (before padding): (219,)
Shape of Total_trx normalized_values (after padding): (1000,)
Shape of Total_item normalized_values (before padding): (680,)
Shape of Total_item normalized_values (after padding): (1000,)
Shape of Total_unique_items normalized_values (before padding): (453,)
Shape of Total_unique_items normalized_values (after padding): (1000,)
Shape of Total_unique_subclasses normalized_values (before padding): (231,)
Shape of Total_unique_subclasses normalized_values (after padding): (1000,)
Shape of Total_unique_subdepartments normalized_values (before padding): (79,)
Shape of Total_unique_subdepartments normalized_values (after padding): (1000,)
Shape of Min_spend normalized_values (before padding): (92,)
Shape of Min_spend normalized_values (after padding): (1000,)
Shape of Max_spend normalized_values (before padding): (681,)
Shape of Max_spend normalized_values (after padding): (1000,)
Shape of days_since_last_purchase normalized_values (before padding): (74,)
Shape of days_since_last_purchase normalized_values (after padding): (1000,)
Shape of days_since_first_purchase normalized_values (before padding): (79,)
Shape of days_since_first_purchase normalized_values (after padding): (1000,)
Shape of spend_per_trx normalized_values (before padding): (1000,)
Shape of Items_per_trx normalized_values (before padding): (21,)
Shape of Items_per_trx normalized_values (after padding): (1000,)
Shape of Unique_items_per_trx normalized_values (before padding): (11,)
Shape of Unique_items_per_trx normalized_values (after padding): (1000,)
Shape of final_concatenated_tensor: (1000, 136)
Shape of member_embeddings: (1000, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (before padding): (140, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (before padding): (160, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (before padding): (150, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (before padding): (152, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (before padding): (143, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (before padding): (168, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (before padding): (169, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (before padding): (166, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (before padding): (154, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (before padding): (147, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (before padding): (177, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (before padding): (185, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (before padding): (136, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (before padding): (163, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (before padding): (182, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (before padding): (180, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (before padding): (402, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (before padding): (531, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (before padding): (561, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (before padding): (583, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (before padding): (401, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (before padding): (523, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (before padding): (560, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (before padding): (602, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (before padding): (366, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (before padding): (457, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (before padding): (515, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (before padding): (541, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (before padding): (585, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (before padding): (352, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (before padding): (432, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (before padding): (495, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (before padding): (535, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (before padding): (558, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of Total_spend normalized_values (before padding): (999,)
Shape of Total_spend normalized_values (after padding): (1000,)
Shape of Total_trx normalized_values (before padding): (219,)
Shape of Total_trx normalized_values (after padding): (1000,)
Shape of Total_item normalized_values (before padding): (680,)
Shape of Total_item normalized_values (after padding): (1000,)
Shape of Total_unique_items normalized_values (before padding): (453,)
Shape of Total_unique_items normalized_values (after padding): (1000,)
Shape of Total_unique_subclasses normalized_values (before padding): (231,)
Shape of Total_unique_subclasses normalized_values (after padding): (1000,)
Shape of Total_unique_subdepartments normalized_values (before padding): (79,)
Shape of Total_unique_subdepartments normalized_values (after padding): (1000,)
Shape of Min_spend normalized_values (before padding): (92,)
Shape of Min_spend normalized_values (after padding): (1000,)
Shape of Max_spend normalized_values (before padding): (681,)
Shape of Max_spend normalized_values (after padding): (1000,)
Shape of days_since_last_purchase normalized_values (before padding): (74,)
Shape of days_since_last_purchase normalized_values (after padding): (1000,)
Shape of days_since_first_purchase normalized_values (before padding): (79,)
Shape of days_since_first_purchase normalized_values (after padding): (1000,)
Shape of spend_per_trx normalized_values (before padding): (1000,)
Shape of Items_per_trx normalized_values (before padding): (21,)
Shape of Items_per_trx normalized_values (after padding): (1000,)
Shape of Unique_items_per_trx normalized_values (before padding): (11,)
Shape of Unique_items_per_trx normalized_values (after padding): (1000,)
Shape of final_concatenated_tensor: (1000, 136)
In [52]:
import tensorflow as tf

class ItemModel(tf.keras.Model):
    def __init__(self, unique_Item_ids, unique_features_categorical, unique_features_numerical, embedding_dim=32):
        super().__init__()
        self.embedding_dim = embedding_dim

        # Initialize the embedding layers dictionary
        self.embedding_layers = {}
        
        # Initialize normalization layers
        self.normalization_layers = {}

        # Initialize the Item_id lookup and embedding layer
        self.Item_lookup = tf.keras.layers.StringLookup(vocabulary=unique_Item_ids, mask_token=None, oov_token=None)
        self.Item_embedding_layer = tf.keras.layers.Embedding(input_dim=self.Item_lookup.vocabulary_size(), output_dim=embedding_dim)

        # Create embedding layers for other categorical features
        for feature_name, vocabulary in unique_features_categorical.items():
            if feature_name != 'Item_id':
                lookup = tf.keras.layers.StringLookup(vocabulary=vocabulary, mask_token=None, oov_token=None)
                vocab_size = lookup.vocabulary_size()
                embedding = tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim)
                self.embedding_layers[feature_name] = (lookup, embedding)

        # Create normalization layers for numerical features
        for feature_name in unique_features_numerical:
            normalization_layer = tf.keras.layers.LayerNormalization(axis=-1, epsilon=1e-6)
            self.normalization_layers[feature_name] = normalization_layer

    def call(self, Item_features):
        # Extract Item_id and convert to embeddings
        Item_id = Item_features['Item_id']
        Item_id_indices = self.Item_lookup(Item_id)
        Item_embeddings = self.Item_embedding_layer(Item_id_indices)
        print(f"Shape of Item_embeddings: {Item_embeddings.shape}")

        # Prepare list for concatenation
        concatenated_features = [Item_embeddings]

        # Process categorical features
        for feature_name, feature_values in Item_features.items():
            if feature_name != 'Item_id':
                if feature_name in self.embedding_layers:
                    lookup, embedding = self.embedding_layers[feature_name]
                    feature_indices = lookup(feature_values)
                    feature_embeddings = embedding(feature_indices)
                    print(f"Shape of {feature_name} feature_embeddings (before padding): {feature_embeddings.shape}")

                    # Pad if needed to match batch size of Item_embeddings
                    if feature_embeddings.shape[0] < Item_embeddings.shape[0]:
                        padding_size = Item_embeddings.shape[0] - feature_embeddings.shape[0]
                        feature_embeddings = tf.pad(feature_embeddings, [[0, padding_size], [0, 0]], constant_values=0)
                        print(f"Shape of {feature_name} feature_embeddings (after padding): {feature_embeddings.shape}")
                    
                    concatenated_features.append(feature_embeddings)

        # Process numerical features
        for feature_name, feature_values in Item_features.items():
            if feature_name in self.normalization_layers:
                normalization_layer = self.normalization_layers[feature_name]
                normalized_values = normalization_layer(tf.expand_dims(feature_values, axis=0))
                normalized_values = tf.squeeze(normalized_values, axis=0)
                print(f"Shape of {feature_name} normalized_values (before padding): {normalized_values.shape}")

                # Pad if needed to match batch size
                if normalized_values.shape[0] < Item_embeddings.shape[0]:
                    padding_size = Item_embeddings.shape[0] - normalized_values.shape[0]
                    normalized_values = tf.pad(normalized_values, [[0, padding_size]], constant_values=0)
                    print(f"Shape of {feature_name} normalized_values (after padding): {normalized_values.shape}")
                
                concatenated_features.append(tf.expand_dims(normalized_values, axis=-1))

        # Concatenate all tensors along the last axis
        final_concatenated_tensor = tf.concat(concatenated_features, axis=-1)
        print(f"Shape of final_concatenated_tensor: {final_concatenated_tensor.shape}")
      

        return final_concatenated_tensor
In [53]:
item_model = ItemModel(
    unique_Item_ids=Unique_Item_ids_tf,
    unique_features_categorical=unique_features_items_categorical_tf,
    unique_features_numerical=unique_features_items_numerical_tf,
    embedding_dim=3
)
In [54]:
output_item_embedding = item_model(item_features)
Shape of Item_embeddings: (34663, 3)
Shape of Item_subclass feature_embeddings (before padding): (1374, 3)
Shape of Item_subclass feature_embeddings (after padding): (34663, 3)
Shape of Item_subdepartment feature_embeddings (before padding): (220, 3)
Shape of Item_subdepartment feature_embeddings (after padding): (34663, 3)
Shape of Total_price_7_days normalized_values (before padding): (4776,)
Shape of Total_price_7_days normalized_values (after padding): (34663,)
Shape of Itm_qty_7_days normalized_values (before padding): (272,)
Shape of Itm_qty_7_days normalized_values (after padding): (34663,)
Shape of Trx_count_7_days normalized_values (before padding): (217,)
Shape of Trx_count_7_days normalized_values (after padding): (34663,)
Shape of Total_price_15_days normalized_values (before padding): (7245,)
Shape of Total_price_15_days normalized_values (after padding): (34663,)
Shape of Itm_qty_15_days normalized_values (before padding): (434,)
Shape of Itm_qty_15_days normalized_values (after padding): (34663,)
Shape of Trx_count_15_days normalized_values (before padding): (346,)
Shape of Trx_count_15_days normalized_values (after padding): (34663,)
Shape of Total_price_60_days normalized_values (before padding): (13710,)
Shape of Total_price_60_days normalized_values (after padding): (34663,)
Shape of Itm_qty_60_days normalized_values (before padding): (951,)
Shape of Itm_qty_60_days normalized_values (after padding): (34663,)
Shape of Trx_count_60_days normalized_values (before padding): (738,)
Shape of Trx_count_60_days normalized_values (after padding): (34663,)
Shape of Total_price_90_days normalized_values (before padding): (16172,)
Shape of Total_price_90_days normalized_values (after padding): (34663,)
Shape of Itm_qty_90_days normalized_values (before padding): (1193,)
Shape of Itm_qty_90_days normalized_values (after padding): (34663,)
Shape of Trx_count_90_days normalized_values (before padding): (947,)
Shape of Trx_count_90_days normalized_values (after padding): (34663,)
Shape of final_concatenated_tensor: (34663, 21)
Shape of Item_embeddings: (34663, 3)
Shape of Item_subclass feature_embeddings (before padding): (1374, 3)
Shape of Item_subclass feature_embeddings (after padding): (34663, 3)
Shape of Item_subdepartment feature_embeddings (before padding): (220, 3)
Shape of Item_subdepartment feature_embeddings (after padding): (34663, 3)
Shape of Total_price_7_days normalized_values (before padding): (4776,)
Shape of Total_price_7_days normalized_values (after padding): (34663,)
Shape of Itm_qty_7_days normalized_values (before padding): (272,)
Shape of Itm_qty_7_days normalized_values (after padding): (34663,)
Shape of Trx_count_7_days normalized_values (before padding): (217,)
Shape of Trx_count_7_days normalized_values (after padding): (34663,)
Shape of Total_price_15_days normalized_values (before padding): (7245,)
Shape of Total_price_15_days normalized_values (after padding): (34663,)
Shape of Itm_qty_15_days normalized_values (before padding): (434,)
Shape of Itm_qty_15_days normalized_values (after padding): (34663,)
Shape of Trx_count_15_days normalized_values (before padding): (346,)
Shape of Trx_count_15_days normalized_values (after padding): (34663,)
Shape of Total_price_60_days normalized_values (before padding): (13710,)
Shape of Total_price_60_days normalized_values (after padding): (34663,)
Shape of Itm_qty_60_days normalized_values (before padding): (951,)
Shape of Itm_qty_60_days normalized_values (after padding): (34663,)
Shape of Trx_count_60_days normalized_values (before padding): (738,)
Shape of Trx_count_60_days normalized_values (after padding): (34663,)
Shape of Total_price_90_days normalized_values (before padding): (16172,)
Shape of Total_price_90_days normalized_values (after padding): (34663,)
Shape of Itm_qty_90_days normalized_values (before padding): (1193,)
Shape of Itm_qty_90_days normalized_values (after padding): (34663,)
Shape of Trx_count_90_days normalized_values (before padding): (947,)
Shape of Trx_count_90_days normalized_values (after padding): (34663,)
Shape of final_concatenated_tensor: (34663, 21)
In [55]:
member_features = {feature_name: tf.constant(values) for feature_name, values in unique_features_members_combined.items()}

#Print the result to verify
for feature_name, tensor in member_features.items():
    print(f"Feature: {feature_name}")
    print(f"Tensor: {tensor.numpy()}")
    
item_features = {feature_name: tf.constant(values) for feature_name, values in unique_features_items_combined.items()}

#Print the result to verify
for feature_name, tensor in member_features.items():
    print(f"Feature: {feature_name}")
    print(f"Tensor: {tensor.numpy()}")    
Feature: Member_id
Tensor: [b'124334' b'6765190' b'12' b'3902052' b'168740' b'6450644' b'4562'
 b'51972' b'284' b'44238' b'216' b'8739954' b'39274' b'42198' b'12956'
 b'106868' b'53198' b'13060' b'39882' b'40594' b'44074' b'170' b'4147466'
 b'33606' b'1343564' b'108' b'258' b'39812' b'43342' b'9613730' b'13036'
 b'50366' b'2208732' b'39926' b'8106' b'7990616' b'2961522' b'38554'
 b'154' b'95314' b'38828' b'3215042' b'28440' b'42324' b'42136' b'39774'
 b'5156212' b'2484' b'4160930' b'12946' b'44338' b'3861806' b'13056'
 b'282' b'5787444' b'46616' b'42342' b'7918' b'49190' b'108728' b'146986'
 b'1159308' b'1228848' b'12958' b'2806864' b'43306' b'12600' b'88'
 b'40206' b'8180372' b'7545546' b'1299470' b'40856' b'149206' b'48784'
 b'44146' b'10862' b'6299724' b'42190' b'127076' b'3212' b'12908'
 b'2494898' b'6124522' b'862986' b'4244724' b'330' b'42760' b'9090622'
 b'127558' b'42294' b'228658' b'450648' b'7914' b'3063116' b'174'
 b'267292' b'10888' b'40798' b'651944' b'41174' b'2200558' b'10502' b'134'
 b'7894442' b'416692' b'2988' b'5944354' b'143050' b'1983758' b'45340'
 b'108686' b'278320' b'7142292' b'10852' b'308454' b'2065758' b'13040'
 b'7443562' b'325464' b'12902' b'171650' b'9314264' b'256' b'154962'
 b'702968' b'414812' b'296' b'1624616' b'42188' b'5218530' b'2305294'
 b'28824' b'292' b'39848' b'38544' b'91500' b'47354' b'4109950' b'44286'
 b'43122' b'410394' b'512060' b'307348' b'4200804' b'24680' b'6754426'
 b'13080' b'6062346' b'8927630' b'4539922' b'5337916' b'124264' b'48384'
 b'43850' b'5685516' b'408250' b'47512' b'78716' b'2850464' b'42302'
 b'13016' b'9160' b'1988138' b'86' b'299996' b'2479546' b'40456' b'654654'
 b'11300' b'41508' b'516892' b'174644' b'406980' b'156702' b'83996'
 b'13004' b'2200870' b'13062' b'8188696' b'527260' b'2867512' b'96718'
 b'6324' b'3961372' b'7396626' b'2262208' b'40656' b'119380' b'9127496'
 b'1277310' b'389828' b'5142878' b'2802666' b'6522868' b'157318' b'184562'
 b'105034' b'118' b'300694' b'6768022' b'12968' b'6260' b'541894'
 b'4999036' b'627212' b'22892' b'2543574' b'4678236' b'43712' b'2258044'
 b'6417010' b'1241626' b'1023626' b'4606' b'136310' b'41758' b'375586'
 b'45766' b'7724514' b'140' b'9204346' b'111212' b'1568220' b'41826'
 b'40580' b'83766' b'2484116' b'110' b'3851122' b'13438' b'528348'
 b'142590' b'905350' b'1078994' b'12990' b'1629674' b'363210' b'40854'
 b'44128' b'244' b'9620590' b'44560' b'2781138' b'114558' b'1719104'
 b'1634816' b'147256' b'43002' b'23198' b'44300' b'1241870' b'111866'
 b'1639798' b'6841092' b'9750390' b'12982' b'39876' b'6888458' b'154120'
 b'80410' b'276432' b'333510' b'151886' b'1177670' b'272816' b'416664'
 b'7759636' b'82' b'7751352' b'44588' b'42346' b'12828' b'440070' b'78'
 b'7868386' b'126' b'9064996' b'13466' b'8236906' b'6705892' b'190614'
 b'158660' b'686548' b'218' b'41240' b'265076' b'6408' b'230990' b'323358'
 b'755258' b'409042' b'182' b'420796' b'7590056' b'100924' b'13426'
 b'1966316' b'5423266' b'7752936' b'42354' b'443200' b'6114926' b'6414'
 b'39414' b'8793936' b'40418' b'690920' b'2028' b'13112' b'40090' b'21828'
 b'6610964' b'380988' b'384' b'391784' b'189070' b'9175152' b'45154'
 b'1194310' b'34908' b'78768' b'5574' b'31288' b'6824350' b'39834'
 b'44612' b'46598' b'2184766' b'578904' b'34720' b'387216' b'44680'
 b'39806' b'13436' b'6' b'1011566' b'1055992' b'335404' b'42488' b'8384'
 b'13552' b'3304044' b'12874' b'686832' b'314492' b'2560' b'274' b'40104'
 b'231508' b'49992' b'9572610' b'116376' b'322' b'2059202' b'42232'
 b'5449896' b'2283888' b'851600' b'47008' b'341932' b'8460192' b'1762012'
 b'8919972' b'308898' b'9253342' b'5058274' b'3069652' b'39396' b'41190'
 b'1701892' b'151338' b'158824' b'12962' b'2775016' b'445134' b'2258354'
 b'2508064' b'7029696' b'268680' b'9346750' b'4220844' b'8716' b'2144600'
 b'1202290' b'1933310' b'2829106' b'8934566' b'2063998' b'13378' b'45066'
 b'48980' b'593940' b'2652' b'40498' b'322136' b'44944' b'8028468'
 b'417552' b'7612456' b'7492566' b'3875072' b'3868872' b'2474510'
 b'495566' b'56202' b'41096' b'4511010' b'1087754' b'2217176' b'613368'
 b'42664' b'52100' b'5334926' b'3769458' b'80076' b'12894' b'9151844'
 b'301482' b'2739188' b'5142264' b'2428698' b'197590' b'480814' b'328'
 b'9490596' b'565362' b'48844' b'286' b'40846' b'342108' b'37638'
 b'335910' b'12918' b'105584' b'5408764' b'8509440' b'384156' b'42168'
 b'6743738' b'40658' b'5188844' b'722506' b'5536452' b'42262' b'45100'
 b'12914' b'180376' b'4215708' b'346562' b'4213864' b'150' b'611150'
 b'341564' b'73336' b'636190' b'228892' b'4050686' b'418046' b'4217848'
 b'9087796' b'124106' b'42326' b'43190' b'7602868' b'3222166' b'4559600'
 b'362374' b'8489566' b'6886520' b'3014622' b'7573488' b'5126982'
 b'8972988' b'13044' b'2602716' b'339454' b'1431556' b'10930' b'7938660'
 b'9645742' b'8317256' b'5325926' b'132' b'1008924' b'12906' b'37576'
 b'7804492' b'43856' b'5733092' b'5437546' b'42452' b'8527452' b'4372262'
 b'16086' b'54' b'42784' b'2906766' b'39954' b'12830' b'12910' b'1332120'
 b'5663142' b'1454538' b'8786792' b'1148858' b'874058' b'40430' b'42844'
 b'2803540' b'7274928' b'5006352' b'172330' b'964808' b'313734' b'53790'
 b'8295482' b'1350484' b'9120462' b'308' b'8532322' b'896422' b'10210472'
 b'8069214' b'40696' b'130144' b'105228' b'8423364' b'2727130' b'613082'
 b'4285350' b'151528' b'3489610' b'8717516' b'3977188' b'97138' b'7719530'
 b'270384' b'9480420' b'47672' b'1001862' b'43596' b'6369268' b'23892'
 b'299666' b'2711250' b'8716280' b'4095390' b'3690' b'266' b'52164'
 b'3404398' b'40326' b'2950662' b'576150' b'9173188' b'8180554' b'12952'
 b'580012' b'508024' b'43666' b'7966810' b'948804' b'663212' b'8499334'
 b'8061706' b'49286' b'3808' b'7881562' b'57268' b'46400' b'332402'
 b'8058340' b'1322894' b'7763546' b'6402514' b'722168' b'332334'
 b'6214036' b'24340' b'35094' b'5416586' b'2565688' b'166608' b'48176'
 b'105370' b'41844' b'46128' b'46' b'1284120' b'277600' b'176' b'5254528'
 b'441572' b'8771680' b'12924' b'7612414' b'42914' b'50822' b'43128'
 b'197922' b'42370' b'874580' b'269736' b'326' b'49668' b'1250582'
 b'6297860' b'279954' b'389710' b'1416766' b'40948' b'40758' b'50588'
 b'1813540' b'418124' b'1192120' b'28142' b'210552' b'8273936' b'810'
 b'39948' b'56366' b'7699444' b'45140' b'44094' b'2429002' b'4439448'
 b'4134756' b'7949542' b'797244' b'3400600' b'243662' b'195944' b'207132'
 b'1261946' b'61910' b'12880' b'1693480' b'232' b'52132' b'548628'
 b'45480' b'4200516' b'1919968' b'265176' b'850780' b'44042' b'234316'
 b'190326' b'13524' b'13134' b'765630' b'2551496' b'13628' b'731294'
 b'678836' b'155128' b'2977876' b'139190' b'33360' b'44480' b'2351218'
 b'9804124' b'1553824' b'375534' b'161530' b'309098' b'39836' b'418952'
 b'635116' b'136680' b'795854' b'2556888' b'296010' b'44456' b'1655624'
 b'466096' b'273262' b'753274' b'450522' b'336380' b'147980' b'904812'
 b'273136' b'3765514' b'100246' b'12920' b'2144262' b'38812' b'40072'
 b'1013382' b'64' b'9077888' b'9799128' b'830220' b'9131984' b'167654'
 b'2274594' b'4690242' b'24' b'13068' b'2466770' b'7556600' b'6824338'
 b'484984' b'12942' b'8158600' b'1024040' b'8002190' b'2921654' b'44388'
 b'153690' b'37552' b'48140' b'2173166' b'8354156' b'181422' b'1069306'
 b'187764' b'1170402' b'49442' b'657152' b'1768200' b'273122' b'5536498'
 b'44464' b'268' b'162248' b'2211854' b'510294' b'1557280' b'4389822'
 b'3106488' b'10379954' b'7334412' b'680442' b'5754078' b'6551786'
 b'645874' b'9072062' b'602' b'3064814' b'40064' b'40922' b'48792'
 b'353008' b'3943038' b'440860' b'41100' b'725178' b'3706522' b'49310'
 b'3223828' b'2348204' b'1834646' b'9404992' b'95252' b'40180' b'2978858'
 b'1639972' b'143928' b'1200390' b'376562' b'41092' b'86834' b'7659560'
 b'1866' b'1546508' b'9176102' b'3721646' b'264586' b'48064' b'706158'
 b'44154' b'1245808' b'151508' b'43456' b'43310' b'5382034' b'5689306'
 b'762102' b'3956196' b'42466' b'195266' b'590686' b'530258' b'43496'
 b'393802' b'45916' b'45384' b'2376' b'6566018' b'657838' b'147078'
 b'185670' b'1993624' b'44434' b'40478' b'28340' b'9088890' b'310838'
 b'9480124' b'53834' b'477574' b'45612' b'994596' b'431244' b'7086294'
 b'269346' b'543774' b'1686384' b'5566196' b'3605846' b'43264' b'276'
 b'8777612' b'359912' b'9485732' b'6769736' b'44744' b'115024' b'40082'
 b'5721248' b'755690' b'624326' b'233502' b'44288' b'180' b'164570'
 b'130534' b'1168952' b'294' b'870212' b'1214010' b'40714' b'119648'
 b'467442' b'42650' b'46158' b'44840' b'39944' b'265744' b'3684446'
 b'8645336' b'48252' b'272' b'9949618' b'45432' b'46476' b'37580' b'162'
 b'7715552' b'44130' b'2416768' b'325264' b'188720' b'46988' b'131396'
 b'231106' b'2326048' b'152022' b'45736' b'9901020' b'400144' b'732662'
 b'751438' b'332102' b'366048' b'844102' b'121590' b'1165844' b'42344'
 b'40840' b'9635830' b'22' b'7930874' b'125426' b'254' b'42922' b'462954'
 b'1091510' b'74930' b'29434' b'40830' b'5063234' b'53192' b'12970'
 b'851232' b'640460' b'196' b'265720' b'39190' b'1148866' b'9224874'
 b'1225456' b'146580' b'9326534' b'999490' b'115960' b'823450' b'5091926'
 b'46914' b'9319188' b'142368' b'7006352' b'7434996' b'1149362' b'1882452'
 b'460948' b'6542998' b'6194036' b'596054' b'1422648' b'387560' b'304862'
 b'28346' b'33670' b'374700' b'3570442' b'1745166' b'5033204' b'42330'
 b'2166702' b'167458' b'13400' b'731450' b'2913876' b'202' b'13070'
 b'44274' b'9489092' b'6283362' b'109570' b'42172' b'9493760' b'1667226'
 b'53402' b'43482' b'744608' b'5862740' b'156770' b'3864516' b'159106'
 b'192' b'38314' b'34786' b'74894' b'3603276' b'4886474' b'588436'
 b'57838' b'773094' b'967110' b'312356' b'9676594' b'2849856' b'9172576'
 b'6896848' b'41276' b'353386' b'7141192' b'495436' b'9391646' b'753796'
 b'9986782' b'126006' b'4331106' b'6069720' b'3583172' b'46776' b'42736'
 b'224640' b'922256' b'42722' b'8538678' b'12966' b'453186' b'2790012'
 b'40938' b'3044676' b'2008128' b'5634786' b'236918' b'3626084' b'8359702'
 b'2809316' b'3989940' b'1079580' b'10233910' b'39470' b'43792' b'7808958'
 b'2964666' b'245982' b'4296148' b'1395516' b'523170' b'90' b'40968']
Feature: top_1_7_day_fresh_product
Tensor: [b'3860' b'1264' b'44' b'1260' b'NA' b'156' b'1448' b'176' b'13416'
 b'8764' b'811012' b'100' b'51224' b'438616' b'1164' b'48' b'3500'
 b'41608' b'1532' b'2124' b'57776' b'7732' b'1192' b'6716' b'811020'
 b'79080' b'74448' b'4224' b'1180' b'555620' b'41428' b'148984' b'6732'
 b'5996' b'4452' b'2764' b'6936' b'66816' b'188' b'72512' b'67576'
 b'110564' b'3160' b'5752' b'52' b'420336' b'11792' b'2116' b'3048'
 b'1376' b'8328' b'2312' b'949864' b'2500' b'2564' b'3176' b'10884'
 b'87484' b'732924' b'49792' b'2120' b'4744' b'1340' b'2320' b'49776'
 b'90068' b'49384' b'64836' b'66104' b'2692' b'1504' b'3080' b'555576'
 b'264088' b'9272' b'41432' b'1372' b'811076' b'2720' b'77312' b'3188'
 b'556188' b'41768' b'64128' b'245408' b'4416' b'7324' b'6000' b'6724'
 b'121676' b'3376' b'1444' b'61244' b'68100' b'71800' b'9264' b'3356'
 b'2316' b'76108' b'49780' b'88576' b'1172' b'123724' b'93652' b'71364'
 b'32824' b'65464' b'3184' b'5552' b'67956' b'7128' b'81188' b'52112'
 b'52140' b'2160' b'3504' b'57700' b'8248' b'458128' b'67940' b'151976'
 b'49600' b'188700' b'81764' b'88740' b'429736' b'48012' b'4348' b'9852'
 b'5712' b'5092' b'52084' b'83576' b'65568' b'41452' b'8072' b'73000'
 b'914204' b'6124' b'2596']
Feature: top_2_7_day_fresh_product
Tensor: [b'44' b'8520' b'176' b'2120' b'NA' b'188' b'3356' b'1164' b'1260'
 b'811428' b'2764' b'13416' b'1444' b'2692' b'1264' b'1376' b'41452'
 b'133116' b'96956' b'2116' b'156' b'327444' b'4744' b'48012' b'14468'
 b'52' b'1192' b'2564' b'66308' b'1372' b'57704' b'811772' b'3500'
 b'462508' b'2124' b'8764' b'41432' b'52108' b'555748' b'148984' b'1176'
 b'2312' b'9856' b'7324' b'49808' b'4224' b'4416' b'9264' b'100' b'3160'
 b'110564' b'88740' b'1172' b'452212' b'4912' b'6640' b'3080' b'59128'
 b'78348' b'9852' b'259324' b'6128' b'5692' b'93652' b'49784' b'70176'
 b'48' b'5752' b'5092' b'5452' b'732952' b'811076' b'3316' b'41120'
 b'49792' b'64128' b'3184' b'3732' b'76108' b'49616' b'10920' b'1504'
 b'811012' b'1532' b'49788' b'6724' b'1180' b'3504' b'41428' b'2316'
 b'74796' b'49384' b'41756' b'71800' b'452304' b'811120' b'215600' b'9568'
 b'3176' b'235472' b'144528' b'67052' b'65964' b'5744' b'458128' b'5996'
 b'811192' b'16296' b'121676' b'10000' b'4348' b'66924' b'65564' b'62604'
 b'90024' b'2720' b'64132' b'4828' b'12872' b'77312' b'6732' b'3020'
 b'1448' b'61244' b'3048' b'6936' b'64836' b'811024' b'3376' b'7732'
 b'7872' b'2320' b'188620' b'74448' b'67116' b'41380' b'66816' b'65144'
 b'67956' b'90068' b'54124' b'78388' b'4840' b'54148' b'7128' b'446792'
 b'717000' b'944936' b'49780' b'16336' b'49800' b'37132' b'452220' b'2560'
 b'60580' b'452240' b'839892' b'452244' b'41540' b'151976' b'41352'
 b'41324' b'112436' b'67576' b'70448' b'214460' b'11792' b'41216' b'2204'
 b'54160']
Feature: top_3_7_day_fresh_product
Tensor: [b'156' b'176' b'1260' b'78400' b'188' b'NA' b'1164' b'4452' b'74448'
 b'1264' b'2116' b'811020' b'327444' b'41452' b'2764' b'33652' b'4744'
 b'6936' b'1372' b'106660' b'62604' b'2316' b'3356' b'3160' b'148984'
 b'66572' b'93652' b'3048' b'2500' b'67116' b'100' b'77312' b'2312'
 b'2120' b'70412' b'1444' b'44' b'1532' b'49808' b'1176' b'1172' b'52'
 b'48' b'555784' b'1192' b'11152' b'49816' b'7324' b'77808' b'11596'
 b'1448' b'5048' b'1376' b'2692' b'2124' b'41204' b'74796' b'14468'
 b'67956' b'10652' b'59128' b'613360' b'41768' b'3860' b'41464' b'4348'
 b'75904' b'41776' b'3188' b'8248' b'49464' b'9856' b'49800' b'5752'
 b'66308' b'70940' b'54124' b'811964' b'86792' b'4828' b'71800' b'1504'
 b'555576' b'7872' b'4416' b'3080' b'90068' b'76108' b'49456' b'64132'
 b'10920' b'8764' b'37120' b'65568' b'452324' b'5744' b'3176' b'86852'
 b'48012' b'6640' b'41380' b'64128' b'110564' b'54160' b'2720' b'64572'
 b'9568' b'2320' b'3184' b'41604' b'96956' b'3364' b'41428' b'452220'
 b'67268' b'3500' b'452352' b'9272' b'2564' b'67576' b'120284' b'70448'
 b'2160' b'6124' b'8168' b'77516' b'6724' b'41312' b'605148' b'188700'
 b'3504' b'99268' b'452244' b'6128' b'1180' b'5692' b'52188' b'959780'
 b'90024' b'185620' b'71284' b'555588' b'103652' b'2596' b'438616'
 b'242736' b'458128' b'336724' b'13416' b'37136' b'77544' b'4836' b'85268'
 b'65564' b'4224' b'51224' b'10000' b'564916' b'41120' b'65464']
Feature: top_4_7_day_fresh_product
Tensor: [b'1260' b'2160' b'1264' b'79028' b'NA' b'4912' b'2124' b'1164' b'4828'
 b'2316' b'156' b'32824' b'9232' b'2692' b'3188' b'93652' b'100' b'2204'
 b'64836' b'4224' b'77684' b'176' b'9264' b'3176' b'14652' b'1376' b'2120'
 b'3160' b'8248' b'1532' b'1448' b'3500' b'90068' b'6640' b'9856' b'2564'
 b'1176' b'188' b'8520' b'2312' b'54124' b'1504' b'74448' b'2764' b'44'
 b'52' b'3356' b'4744' b'1172' b'52096' b'110564' b'5048' b'438616'
 b'1180' b'185620' b'77312' b'62604' b'361736' b'4452' b'1444' b'2116'
 b'1192' b'5744' b'3504' b'11260' b'10920' b'65884' b'48' b'1340' b'6732'
 b'94608' b'41428' b'52112' b'41352' b'13416' b'452352' b'6724' b'7920'
 b'3184' b'41432' b'41324' b'2500' b'70372' b'4416' b'14468' b'11152'
 b'3732' b'1372' b'65144' b'8328' b'49612' b'235772' b'7324' b'61244'
 b'77516' b'66924' b'67940' b'33736' b'2720' b'78400' b'7732' b'98700'
 b'41388' b'1156' b'452304' b'54148' b'259324' b'11792' b'49640' b'7480'
 b'67956' b'787368' b'99560' b'65568' b'52140' b'108772' b'780612'
 b'264088' b'6936' b'103652' b'49800' b'3080' b'452244' b'142956' b'76108'
 b'5452' b'3168' b'988024' b'10000' b'71800' b'41312' b'88740' b'811008'
 b'235472' b'65132' b'613360' b'34476' b'41756' b'67052' b'5568' b'74796'
 b'188700' b'148984' b'214460' b'5724' b'78288' b'816568' b'144528'
 b'59128' b'112436']
Feature: top_5_7_day_fresh_product
Tensor: [b'176' b'2320' b'2316' b'NA' b'9856' b'1372' b'66924' b'3080' b'44'
 b'5552' b'2312' b'1260' b'452300' b'2564' b'3732' b'4744' b'110564'
 b'1448' b'2764' b'41428' b'52' b'4452' b'148984' b'3356' b'8764' b'6640'
 b'1264' b'156' b'4416' b'48' b'8520' b'2116' b'2692' b'3860' b'5996'
 b'7128' b'11152' b'74448' b'10432' b'3160' b'61244' b'3188' b'3376'
 b'188620' b'9264' b'77312' b'2124' b'1164' b'1192' b'555576' b'1532'
 b'5568' b'839892' b'5692' b'2120' b'4912' b'4828' b'11792' b'1176'
 b'90024' b'151976' b'77000' b'188' b'1444' b'14468' b'74780' b'41204'
 b'7324' b'75564' b'59128' b'49808' b'188700' b'52192' b'3504' b'811008'
 b'77684' b'173104' b'5092' b'5744' b'90660' b'67956' b'8248' b'65564'
 b'140080' b'81896' b'52140' b'822276' b'777184' b'4224' b'62604' b'7732'
 b'76108' b'93652' b'64836' b'92396' b'103652' b'2324' b'52112' b'66520'
 b'79028' b'74796' b'41120' b'70376' b'66820' b'259324' b'3364' b'1504'
 b'2720' b'10304' b'41452' b'41756' b'41432' b'41604' b'64132' b'3500'
 b'787456' b'64572' b'811108' b'65144' b'12884' b'9844' b'71800' b'787256'
 b'57704' b'7872' b'78400' b'1172' b'811024' b'49780' b'214460' b'6716'
 b'2596' b'1376' b'3048' b'3184' b'41464' b'57692' b'90068' b'85792'
 b'361736' b'811428' b'100' b'41716' b'66104' b'37120' b'71260' b'33652'
 b'6936' b'51224' b'215984' b'102644' b'235472']
Feature: top_1_15_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'176' b'156' b'NA' b'66924' b'13416' b'8764'
 b'811020' b'100' b'51224' b'438616' b'6936' b'1164' b'2312' b'458128'
 b'52' b'1340' b'2116' b'2124' b'77312' b'7128' b'3500' b'2120' b'2316'
 b'4744' b'4224' b'3376' b'1532' b'1180' b'555620' b'235772' b'4416'
 b'5048' b'2764' b'188' b'67576' b'110564' b'1444' b'11792' b'3356'
 b'59128' b'1376' b'11260' b'10920' b'949864' b'1192' b'90068' b'5092'
 b'10884' b'87484' b'732924' b'49792' b'3316' b'74448' b'93652' b'41452'
 b'103652' b'3160' b'48' b'67116' b'76108' b'49384' b'1172' b'66104'
 b'811012' b'3080' b'3504' b'41428' b'3732' b'49480' b'452244' b'555576'
 b'264088' b'41756' b'1504' b'2376' b'811076' b'2720' b'1448' b'37120'
 b'3188' b'556188' b'64656' b'41768' b'2692' b'452304' b'5744' b'7324'
 b'16296' b'62604' b'2564' b'4348' b'148984' b'8328' b'9264' b'141148'
 b'49780' b'88576' b'4912' b'7732' b'1372' b'6716' b'123724' b'9856'
 b'41120' b'3860' b'54124' b'5552' b'67956' b'52112' b'2160' b'10648'
 b'57700' b'2500' b'2320' b'6640' b'49800' b'1176' b'57708' b'67940'
 b'151976' b'8168' b'49600' b'188700' b'81764' b'119944' b'922492'
 b'48012' b'78400' b'5712' b'52084' b'83576' b'361736' b'4452' b'41324'
 b'65568' b'10656' b'6732' b'914204' b'6124' b'2596']
Feature: top_2_15_day_fresh_product
Tensor: [b'44' b'8520' b'176' b'1164' b'NA' b'188' b'1264' b'41428' b'100' b'1260'
 b'811428' b'2764' b'2316' b'1444' b'2692' b'2116' b'41452' b'133116'
 b'3080' b'9264' b'2312' b'156' b'4744' b'14468' b'110564' b'2564'
 b'57776' b'10884' b'7732' b'1372' b'1448' b'3500' b'88576' b'8764'
 b'79080' b'1532' b'1376' b'11152' b'452352' b'555748' b'10816' b'41608'
 b'1176' b'1192' b'7324' b'12064' b'4224' b'77312' b'2124' b'4452'
 b'41120' b'41772' b'3160' b'88740' b'2596' b'48' b'2320' b'1172' b'74448'
 b'420336' b'6640' b'9856' b'52' b'67956' b'6724' b'77000' b'246112'
 b'2120' b'93652' b'6936' b'3184' b'732952' b'811076' b'188620' b'945464'
 b'49776' b'64128' b'41768' b'3732' b'49616' b'54124' b'1504' b'65564'
 b'452252' b'48012' b'70372' b'1180' b'66924' b'41540' b'9272' b'8328'
 b'49384' b'71800' b'76108' b'71260' b'3356' b'5712' b'67052' b'65964'
 b'452244' b'811192' b'438616' b'6000' b'85104' b'41380' b'787368' b'3188'
 b'235472' b'10000' b'121676' b'87344' b'66820' b'10920' b'62604' b'61244'
 b'452304' b'12872' b'2720' b'64836' b'7480' b'49800' b'3376' b'4416'
 b'2160' b'6124' b'71364' b'4912' b'65568' b'787256' b'235772' b'11596'
 b'11752' b'3176' b'581832' b'90068' b'81188' b'3504' b'52192' b'2500'
 b'1340' b'2376' b'59128' b'7128' b'57704' b'446792' b'717000' b'944936'
 b'8248' b'41716' b'458128' b'60580' b'839892' b'79028' b'4348' b'64132'
 b'5744' b'151976' b'41352' b'2324' b'67576' b'16296' b'214460' b'70316'
 b'87976' b'41216' b'2204' b'34484' b'54160']
Feature: top_3_15_day_fresh_product
Tensor: [b'156' b'176' b'1260' b'NA' b'1164' b'1448' b'44' b'7732' b'2116'
 b'811012' b'327444' b'41452' b'2764' b'33652' b'452300' b'1264' b'1376'
 b'48' b'2312' b'2692' b'3188' b'8764' b'41120' b'90068' b'452352' b'2120'
 b'3160' b'148984' b'1532' b'41428' b'93652' b'188' b'1192' b'52' b'100'
 b'67116' b'3364' b'6716' b'3048' b'945464' b'1372' b'2124' b'49808'
 b'74448' b'613360' b'76108' b'1172' b'556188' b'555784' b'88576' b'66308'
 b'9856' b'11152' b'62604' b'6936' b'41716' b'41324' b'65132' b'1444'
 b'4828' b'77312' b'3860' b'452212' b'4912' b'4416' b'5752' b'86520'
 b'2316' b'59128' b'78348' b'8328' b'1180' b'3356' b'556808' b'3020'
 b'37128' b'6724' b'2564' b'5712' b'4348' b'67956' b'922528' b'8520'
 b'49792' b'173104' b'9272' b'64836' b'2500' b'9852' b'1504' b'555576'
 b'71356' b'74796' b'3080' b'65144' b'48012' b'49456' b'3504' b'64132'
 b'57700' b'78400' b'1176' b'9568' b'3176' b'5744' b'67576' b'245408'
 b'458128' b'14468' b'57708' b'86852' b'110564' b'73008' b'2720' b'41604'
 b'96956' b'54148' b'48780' b'810996' b'120284' b'61244' b'52188' b'41768'
 b'37168' b'41380' b'32824' b'3184' b'99268' b'49800' b'452244' b'179940'
 b'54124' b'5692' b'4452' b'4840' b'52140' b'2596' b'41156' b'73264'
 b'90024' b'41204' b'87344' b'71284' b'555588' b'7324' b'37132' b'48772'
 b'88740' b'3732' b'336724' b'3500' b'37136' b'77544' b'188700' b'121676'
 b'4836' b'85268' b'66816' b'5552' b'2376' b'90852' b'8072' b'51224'
 b'11352' b'5724' b'7128' b'57704' b'564916' b'37124']
Feature: top_4_15_day_fresh_product
Tensor: [b'3860' b'2160' b'1264' b'1448' b'1260' b'NA' b'4452' b'74448' b'1164'
 b'811944' b'13416' b'452324' b'1444' b'3500' b'41756' b'41608' b'452352'
 b'93652' b'176' b'2124' b'11152' b'8764' b'44' b'4416' b'90024' b'3048'
 b'2500' b'1372' b'2764' b'3176' b'2120' b'2116' b'3160' b'90068'
 b'811772' b'1192' b'156' b'462508' b'1532' b'3184' b'110564' b'188' b'52'
 b'14468' b'112436' b'2312' b'52096' b'3504' b'76108' b'66816' b'65964'
 b'78348' b'438616' b'5048' b'2564' b'52188' b'3188' b'1376' b'2692'
 b'2316' b'4224' b'41120' b'79028' b'1176' b'6936' b'1172' b'5744'
 b'16344' b'64132' b'3080' b'9272' b'41768' b'6128' b'49784' b'100' b'48'
 b'5752' b'62604' b'41428' b'1340' b'246112' b'49800' b'839892' b'66308'
 b'2204' b'264088' b'10920' b'41324' b'37132' b'811964' b'49788' b'41604'
 b'71800' b'1504' b'7872' b'3732' b'7732' b'78400' b'49612' b'4744'
 b'7324' b'54124' b'6640' b'452304' b'811120' b'2320' b'41216' b'77516'
 b'3356' b'4912' b'54148' b'555576' b'48012' b'7128' b'67116' b'74796'
 b'4828' b'79064' b'64572' b'452244' b'9568' b'8328' b'452220' b'61244'
 b'67268' b'49596' b'811024' b'787368' b'64764' b'57692' b'65564' b'8168'
 b'605148' b'65144' b'103652' b'121676' b'11260' b'54160' b'76348' b'1180'
 b'10000' b'64128' b'66924' b'811952' b'959780' b'2720' b'70136' b'16336'
 b'811008' b'16280' b'235772' b'241064' b'49492' b'2560' b'452240'
 b'337124' b'67956' b'429736' b'5568' b'9264' b'214460' b'922528'
 b'151976' b'816568' b'144528' b'4200']
Feature: top_5_15_day_fresh_product
Tensor: [b'3500' b'2320' b'2316' b'2120' b'1264' b'NA' b'1372' b'4912' b'64132'
 b'2312' b'14468' b'176' b'839892' b'2124' b'2116' b'3732' b'41452'
 b'54148' b'62604' b'188' b'3356' b'327444' b'48012' b'9264' b'3176'
 b'10816' b'1192' b'3160' b'4828' b'1164' b'156' b'66308' b'52' b'3860'
 b'452244' b'100' b'1260' b'2564' b'1176' b'41432' b'1180' b'1532' b'2376'
 b'54124' b'48' b'2692' b'3184' b'44' b'7324' b'77808' b'10920' b'85268'
 b'361736' b'1172' b'41120' b'1444' b'1448' b'4744' b'3188' b'3080'
 b'6936' b'88740' b'151976' b'2764' b'3504' b'3048' b'65884' b'75756'
 b'76108' b'74448' b'103652' b'2500' b'1340' b'59128' b'49808' b'41464'
 b'71052' b'52084' b'1376' b'8248' b'452352' b'7920' b'16312' b'67116'
 b'70940' b'86792' b'188700' b'52140' b'188620' b'556808' b'235772'
 b'7732' b'5996' b'61244' b'47984' b'92396' b'2560' b'3364' b'120284'
 b'5552' b'2324' b'79028' b'52112' b'33736' b'2720' b'71260' b'74796'
 b'13416' b'57776' b'41604' b'66820' b'93652' b'11152' b'10304' b'4416'
 b'452304' b'259324' b'11792' b'787456' b'70448' b'64128' b'77516' b'8764'
 b'780612' b'52192' b'110564' b'57704' b'811192' b'41428' b'78400'
 b'49796' b'67044' b'4224' b'142956' b'3168' b'41716' b'64536' b'5692'
 b'185620' b'90068' b'235472' b'78132' b'1504' b'438616' b'5048' b'77312'
 b'64656' b'67956' b'840108' b'7128' b'41776' b'6724' b'65464' b'68224']
Feature: top_1_60_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'176' b'8536' b'66924' b'184' b'8764' b'811020'
 b'100' b'1164' b'438616' b'2116' b'2692' b'41608' b'49600' b'2312' b'156'
 b'NA' b'1340' b'52108' b'5716' b'6640' b'4416' b'77312' b'9264' b'7128'
 b'3500' b'1376' b'76108' b'4224' b'1172' b'1180' b'73260' b'98784'
 b'1192' b'9856' b'7324' b'3160' b'12064' b'5048' b'452244' b'613076'
 b'70376' b'48' b'188' b'452212' b'110564' b'3356' b'2124' b'2120' b'52'
 b'1444' b'41464' b'59128' b'77000' b'5552' b'246112' b'556808' b'65884'
 b'74448' b'2500' b'1532' b'57700' b'2564' b'41432' b'732952' b'49792'
 b'3316' b'41452' b'67116' b'49788' b'3080' b'48012' b'6724' b'2764'
 b'3504' b'41428' b'49480' b'2560' b'74796' b'2316' b'41756' b'1504'
 b'6832' b'811076' b'2720' b'1176' b'556188' b'14672' b'41768' b'65964'
 b'452304' b'16296' b'62604' b'4348' b'41324' b'41120' b'34484' b'71260'
 b'5744' b'96956' b'61244' b'3048' b'49780' b'461668' b'103652' b'52188'
 b'1448' b'65568' b'37128' b'49596' b'64132' b'67956' b'811024' b'6716'
 b'65144' b'1372' b'3184' b'71800' b'9272' b'529128' b'54124' b'452368'
 b'811008' b'49808' b'8168' b'51224' b'151976' b'60580' b'2596' b'88740'
 b'78400' b'2160' b'839892' b'83576' b'5712' b'52084' b'361736' b'66104'
 b'10920' b'90068' b'5724' b'914204' b'6936' b'144528' b'4200']
Feature: top_2_60_day_fresh_product
Tensor: [b'44' b'176' b'1264' b'1260' b'NA' b'156' b'2560' b'11596' b'100' b'1164'
 b'811428' b'2316' b'2596' b'41452' b'133116' b'65884' b'65464' b'2116'
 b'2124' b'2764' b'4744' b'64572' b'93652' b'8244' b'88740' b'3500'
 b'2564' b'179940' b'7732' b'74448' b'6716' b'3048' b'3176' b'2120'
 b'8764' b'9856' b'4416' b'1532' b'3376' b'2312' b'1448' b'14672' b'65568'
 b'5048' b'54148' b'70940' b'49808' b'4224' b'77312' b'7324' b'5752'
 b'41120' b'564896' b'1172' b'67576' b'142956' b'3160' b'6936' b'811944'
 b'3504' b'57692' b'188' b'65128' b'8328' b'2320' b'1176' b'52' b'85104'
 b'4828' b'52140' b'5712' b'10884' b'87484' b'811076' b'67940' b'86520'
 b'246112' b'452304' b'1192' b'839892' b'7128' b'48' b'148984' b'1372'
 b'1504' b'41324' b'2720' b'811012' b'49788' b'110564' b'52188' b'66924'
 b'3188' b'49388' b'452244' b'52156' b'9272' b'121676' b'41756' b'2500'
 b'41428' b'52096' b'82408' b'3080' b'37120' b'66820' b'67052' b'438616'
 b'245408' b'2692' b'86852' b'4348' b'4452' b'1444' b'67116' b'3184'
 b'65564' b'64128' b'3364' b'9264' b'10920' b'26792' b'82868' b'452324'
 b'90068' b'49596' b'66308' b'52108' b'7480' b'810996' b'88576' b'4912'
 b'77652' b'65144' b'1180' b'3356' b'81676' b'581832' b'51224' b'2324'
 b'81188' b'52192' b'5996' b'2376' b'184' b'6724' b'2204' b'446792'
 b'76348' b'107676' b'49780' b'49800' b'103652' b'8168' b'64764' b'48012'
 b'41432' b'79028' b'5552' b'49604' b'452300' b'5092' b'82940' b'811000'
 b'62604' b'3732' b'76108' b'57776' b'66104' b'6124']
Feature: top_3_60_day_fresh_product
Tensor: [b'156' b'2312' b'1260' b'44' b'100' b'NA' b'176' b'5744' b'4348' b'1164'
 b'811012' b'3160' b'41452' b'1376' b'33652' b'52140' b'2116' b'1264'
 b'77312' b'7872' b'66308' b'458128' b'1172' b'2316' b'74448' b'3364'
 b'14468' b'141704' b'188' b'1372' b'2764' b'4416' b'246112' b'12064'
 b'1532' b'88576' b'4224' b'811020' b'48784' b'4828' b'49808' b'1180'
 b'9264' b'52' b'452352' b'2564' b'73264' b'2500' b'148984' b'3504'
 b'1192' b'6124' b'3188' b'6936' b'41716' b'2124' b'839892' b'564912'
 b'41380' b'7128' b'949664' b'62604' b'90676' b'556808' b'11908' b'6724'
 b'11260' b'77000' b'48' b'7324' b'8764' b'2320' b'77808' b'2120' b'67956'
 b'1444' b'71052' b'6716' b'8240' b'5048' b'188620' b'71800' b'41428'
 b'41540' b'3080' b'1448' b'847168' b'64128' b'41768' b'54124' b'1408'
 b'2692' b'452252' b'70372' b'71356' b'49472' b'90068' b'70424' b'264088'
 b'8520' b'65144' b'3184' b'2560' b'2376' b'11596' b'6640' b'4744' b'3168'
 b'81188' b'73008' b'811192' b'67576' b'6000' b'74796' b'85104' b'57776'
 b'787368' b'452304' b'121676' b'64132' b'87344' b'2720' b'88740' b'3356'
 b'41604' b'9272' b'8328' b'67940' b'54148' b'3732' b'49596' b'811024'
 b'555576' b'1504' b'452220' b'65568' b'787256' b'1176' b'52192' b'110564'
 b'9856' b'57692' b'49800' b'65548' b'59128' b'41756' b'49488' b'5752'
 b'3048' b'2596' b'76108' b'5552' b'41732' b'65464' b'93652' b'66924'
 b'904620' b'57700' b'7732' b'811772' b'452240' b'65296' b'48772' b'81764'
 b'151976' b'64764' b'3176' b'49792' b'33644' b'83576' b'2160' b'41464'
 b'605148' b'6732' b'41216' b'34484' b'54160']
Feature: top_4_60_day_fresh_product
Tensor: [b'176' b'8520' b'1264' b'NA' b'1260' b'2692' b'1372' b'13416' b'188'
 b'2116' b'811944' b'1164' b'41768' b'1444' b'3080' b'156' b'1448' b'48'
 b'52' b'5048' b'77312' b'100' b'2120' b'44' b'74448' b'4452' b'2764'
 b'2312' b'2500' b'3160' b'581832' b'10884' b'1532' b'3364' b'452240'
 b'41428' b'462508' b'1176' b'438616' b'62604' b'14468' b'2316' b'3176'
 b'246112' b'11152' b'2124' b'9264' b'1192' b'3504' b'110564' b'41324'
 b'2564' b'5744' b'179940' b'41540' b'6936' b'1376' b'67956' b'65884'
 b'1172' b'88740' b'41216' b'79064' b'76108' b'59128' b'37132' b'3184'
 b'10432' b'9272' b'732924' b'4744' b'71264' b'452304' b'49776' b'7128'
 b'839900' b'184' b'8764' b'78400' b'66104' b'41432' b'6320' b'48636'
 b'4416' b'7872' b'8328' b'49600' b'49816' b'3732' b'79636' b'77544'
 b'79028' b'41196' b'41120' b'66308' b'9844' b'4828' b'41604' b'452212'
 b'7732' b'3860' b'185620' b'70376' b'74796' b'90068' b'839892' b'3500'
 b'65548' b'93652' b'3356' b'3188' b'6732' b'86792' b'452220' b'1180'
 b'11792' b'9568' b'3168' b'52140' b'845268' b'41716' b'61244' b'11752'
 b'11908' b'6124' b'8168' b'79080' b'5552' b'41172' b'52156' b'613360'
 b'108772' b'564916' b'64772' b'5692' b'86852' b'52112' b'2560' b'103652'
 b'64128' b'121676' b'5996' b'2720' b'605420' b'2596' b'49784' b'3048'
 b'555576' b'10648' b'87344' b'11596' b'33708' b'810996' b'5860' b'57708'
 b'88576' b'49388' b'188700' b'119944' b'2320' b'67116' b'51224' b'6832'
 b'811076' b'151976' b'214460' b'97240' b'84120' b'92396' b'816568'
 b'78388' b'1504' b'37124' b'8244']
Feature: top_5_60_day_fresh_product
Tensor: [b'1264' b'156' b'2316' b'1164' b'44' b'NA' b'188' b'2120' b'64572'
 b'1172' b'1260' b'78388' b'1448' b'65144' b'6936' b'2312' b'140080'
 b'2764' b'176' b'64836' b'4416' b'13416' b'3048' b'3500' b'7324' b'2692'
 b'5752' b'2124' b'3364' b'100' b'6640' b'2116' b'51224' b'90068' b'9856'
 b'48' b'41812' b'1192' b'41432' b'74448' b'452244' b'52' b'1532'
 b'452300' b'5552' b'1176' b'52096' b'62604' b'438616' b'4452' b'66816'
 b'41732' b'3188' b'2596' b'41120' b'3160' b'64128' b'1376' b'1444'
 b'811052' b'11792' b'3356' b'245720' b'71264' b'1180' b'70372' b'2564'
 b'76108' b'70176' b'77544' b'811000' b'41756' b'41428' b'945464'
 b'787256' b'1372' b'581832' b'5048' b'3080' b'3184' b'5996' b'3504'
 b'3732' b'264088' b'452324' b'49384' b'9272' b'41708' b'9852' b'86792'
 b'41604' b'4828' b'5716' b'14468' b'41540' b'11260' b'59128' b'67940'
 b'88740' b'8764' b'3860' b'93652' b'41716' b'103652' b'2320' b'839900'
 b'64132' b'4348' b'65084' b'5744' b'52140' b'6124' b'2720' b'78400'
 b'41380' b'787456' b'67116' b'206252' b'3176' b'8328' b'452220' b'452304'
 b'66308' b'2308' b'556188' b'65296' b'603460' b'811968' b'65384' b'57700'
 b'603440' b'65564' b'8248' b'64968' b'41768' b'71800' b'65108' b'7732'
 b'605148' b'71260' b'77312' b'4912' b'246112' b'16344' b'9264' b'811428'
 b'79028' b'67956' b'76348' b'5692' b'7872' b'49804' b'845268' b'2500'
 b'2160' b'839892' b'37172' b'4744' b'110564' b'41724' b'109768' b'185620'
 b'12356' b'10920' b'1340' b'377356' b'86520' b'458128' b'54124' b'49600'
 b'12872' b'33652' b'41216' b'4224' b'78432' b'86852' b'607836' b'65568'
 b'70304' b'277204' b'5712' b'74796' b'6724' b'77516' b'2560']
Feature: top_1_90_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'66924' b'176' b'77000' b'11596' b'811020' b'100'
 b'1164' b'438616' b'41452' b'65884' b'49600' b'2312' b'2116' b'1376'
 b'NA' b'8764' b'1340' b'2500' b'5716' b'3500' b'6640' b'4416' b'77312'
 b'12064' b'9264' b'74448' b'7128' b'156' b'52' b'76108' b'4224' b'1172'
 b'1180' b'14672' b'98784' b'9856' b'7324' b'70940' b'452244' b'613076'
 b'564896' b'2316' b'48788' b'2124' b'102640' b'110564' b'3356' b'2120'
 b'2764' b'1444' b'59128' b'5552' b'246112' b'1448' b'3160' b'1532'
 b'57704' b'2564' b'41432' b'732952' b'49792' b'1192' b'3316' b'839892'
 b'67116' b'48012' b'6724' b'2204' b'3504' b'41428' b'49480' b'2560'
 b'41756' b'1372' b'1504' b'6832' b'2720' b'1176' b'556188' b'48'
 b'452304' b'16296' b'4452' b'62604' b'4348' b'41324' b'41120' b'188'
 b'34484' b'88740' b'96956' b'61244' b'11792' b'49780' b'5744' b'461668'
 b'3184' b'103652' b'52188' b'77652' b'49596' b'8328' b'67956' b'811428'
 b'6716' b'3080' b'65144' b'2376' b'57700' b'71800' b'9272' b'529128'
 b'54124' b'811008' b'86520' b'52140' b'8168' b'88576' b'2596' b'78400'
 b'41768' b'2160' b'52084' b'83576' b'361736' b'66104' b'10920' b'90068'
 b'914204' b'54160' b'6936' b'144528' b'4200']
Feature: top_2_90_day_fresh_product
Tensor: [b'44' b'176' b'1260' b'2204' b'156' b'1264' b'3364' b'8764' b'13416'
 b'1164' b'811012' b'2316' b'2596' b'2692' b'140080' b'65464' b'NA'
 b'2764' b'4744' b'64572' b'93652' b'3048' b'52108' b'8244' b'2564'
 b'108772' b'2124' b'581832' b'7732' b'3500' b'1192' b'74448' b'4224'
 b'4828' b'2120' b'9856' b'4416' b'1532' b'1448' b'2116' b'73264' b'3080'
 b'49808' b'2312' b'839892' b'12872' b'48784' b'564912' b'100' b'41432'
 b'188' b'67576' b'142956' b'3160' b'6936' b'4348' b'86520' b'57692'
 b'59128' b'556808' b'78348' b'3504' b'11260' b'52' b'85104' b'52140'
 b'6732' b'5712' b'10884' b'1172' b'71052' b'732924' b'811076' b'452352'
 b'71800' b'780612' b'1376' b'77312' b'1372' b'148984' b'41324' b'37132'
 b'246112' b'52188' b'3188' b'49388' b'74796' b'52156' b'9272' b'8328'
 b'121676' b'1180' b'2500' b'41428' b'2320' b'82408' b'37120' b'66820'
 b'110564' b'14672' b'185620' b'67052' b'5448' b'70412' b'86852' b'9264'
 b'787368' b'452304' b'66924' b'65564' b'41120' b'64128' b'11792' b'1504'
 b'88740' b'5744' b'452212' b'82868' b'3184' b'452324' b'90068' b'14468'
 b'49596' b'48' b'48776' b'1444' b'98700' b'65144' b'6124' b'1176'
 b'922492' b'65568' b'52192' b'51224' b'605420' b'79028' b'67956' b'5048'
 b'81188' b'70740' b'2720' b'184' b'811008' b'6724' b'7128' b'41732'
 b'446792' b'107676' b'438616' b'6640' b'810996' b'76108' b'71260'
 b'151976' b'52096' b'64764' b'60580' b'7324' b'3176' b'49604' b'57700'
 b'5092' b'52084' b'82940' b'62604' b'41352' b'41756' b'5552' b'41452'
 b'57776' b'84120' b'41216' b'10920' b'5724']
Feature: top_3_90_day_fresh_product
Tensor: [b'156' b'2312' b'1260' b'1264' b'176' b'1164' b'5744' b'1372' b'85104'
 b'77000' b'811428' b'3160' b'41452' b'33652' b'2116' b'77312' b'44'
 b'1448' b'7872' b'458128' b'2564' b'2124' b'NA' b'1172' b'3364' b'67940'
 b'14468' b'141704' b'188' b'88740' b'246112' b'100' b'2596' b'811020'
 b'3504' b'49808' b'74448' b'1376' b'37132' b'452352' b'2764' b'1532'
 b'73260' b'9264' b'54148' b'2500' b'5996' b'4416' b'1192' b'6936' b'2120'
 b'564952' b'7128' b'949664' b'62604' b'90676' b'82408' b'6640' b'41464'
 b'3048' b'1444' b'76108' b'8328' b'1180' b'2692' b'52' b'8764' b'48'
 b'77808' b'67956' b'9272' b'2316' b'87484' b'6716' b'65548' b'452304'
 b'93652' b'3080' b'67116' b'64128' b'148984' b'452324' b'1504' b'1408'
 b'65084' b'86792' b'49788' b'70372' b'110564' b'59128' b'49472' b'7732'
 b'65564' b'90068' b'264088' b'65144' b'41756' b'71800' b'52096' b'2376'
 b'41120' b'839900' b'438616' b'81188' b'103652' b'73008' b'9568'
 b'185620' b'74796' b'64132' b'87344' b'7324' b'235472' b'71260' b'3500'
 b'10920' b'68100' b'3356' b'41604' b'2720' b'41428' b'52108' b'3188'
 b'88576' b'4912' b'3376' b'41716' b'4828' b'452220' b'65568' b'9856'
 b'10652' b'581832' b'4224' b'3176' b'11908' b'98784' b'117632' b'4744'
 b'57692' b'68104' b'52156' b'2204' b'2320' b'3184' b'452368' b'49780'
 b'57700' b'65296' b'81764' b'41432' b'4348' b'5552' b'66104' b'452300'
 b'51224' b'121676' b'83576' b'2160' b'811024' b'555576' b'34484' b'6124']
Feature: top_4_90_day_fresh_product
Tensor: [b'176' b'1192' b'1264' b'100' b'49808' b'1164' b'74448' b'44' b'2120'
 b'214460' b'156' b'85104' b'811944' b'41768' b'1376' b'2692' b'3080'
 b'1260' b'52140' b'2116' b'48' b'188' b'52' b'2312' b'7732' b'NA' b'2764'
 b'5048' b'235472' b'3364' b'90068' b'3500' b'7324' b'4416' b'1372'
 b'14468' b'2316' b'10884' b'1532' b'6716' b'9856' b'3048' b'3160'
 b'462508' b'438616' b'1180' b'5744' b'9264' b'1444' b'3376' b'2564'
 b'14652' b'3176' b'1176' b'65568' b'41224' b'246112' b'11152' b'2124'
 b'1448' b'5752' b'3188' b'70376' b'77312' b'41120' b'1172' b'78432'
 b'4452' b'245720' b'65128' b'65884' b'787256' b'79064' b'8520' b'4912'
 b'2204' b'70176' b'8240' b'4744' b'71264' b'49776' b'7128' b'452304'
 b'839892' b'3504' b'5092' b'9272' b'54124' b'2500' b'66104' b'110564'
 b'41432' b'2720' b'6320' b'452252' b'7872' b'92116' b'66924' b'121676'
 b'49600' b'8244' b'452244' b'70424' b'65564' b'76108' b'3184' b'5568'
 b'2560' b'41324' b'65964' b'3732' b'6000' b'4828' b'74796' b'57776'
 b'41716' b'3168' b'8764' b'65548' b'811940' b'2596' b'6936' b'839900'
 b'452220' b'9568' b'8328' b'555576' b'6732' b'67956' b'61244' b'65384'
 b'93652' b'88740' b'41540' b'79080' b'41172' b'52156' b'251052' b'148984'
 b'37128' b'811192' b'49800' b'64132' b'67044' b'2324' b'78400' b'14672'
 b'49784' b'52108' b'5996' b'41428' b'555588' b'344784' b'5552' b'264088'
 b'10656' b'64020' b'11596' b'33708' b'452352' b'62604' b'5860' b'57708'
 b'811772' b'48028' b'564916' b'48772' b'49788' b'377356' b'556808'
 b'581832' b'65144' b'64764' b'8248' b'151976' b'2320' b'97240' b'1504'
 b'452300' b'107604' b'78388' b'37124']
Feature: top_5_90_day_fresh_product
Tensor: [b'1264' b'2316' b'176' b'44' b'1172' b'1260' b'7732' b'188' b'100'
 b'64132' b'78388' b'1444' b'156' b'6936' b'2120' b'65084' b'2312' b'1164'
 b'133116' b'41608' b'NA' b'93652' b'77312' b'74448' b'4452' b'2764' b'52'
 b'67116' b'2124' b'3160' b'2692' b'3504' b'4416' b'179940' b'2116'
 b'1372' b'1192' b'48' b'1176' b'1532' b'3080' b'452244' b'1376' b'452240'
 b'5552' b'52096' b'5744' b'6124' b'41120' b'41324' b'564916' b'1448'
 b'3364' b'64128' b'5752' b'811944' b'2564' b'3048' b'1180' b'3184'
 b'3500' b'2560' b'76108' b'57700' b'4828' b'52108' b'64656' b'4348'
 b'41716' b'452304' b'3860' b'41216' b'581832' b'811000' b'184' b'3188'
 b'3732' b'11596' b'78400' b'557876' b'41708' b'438616' b'5692' b'49788'
 b'2160' b'48636' b'86520' b'2320' b'8328' b'2500' b'71356' b'67940'
 b'8764' b'79028' b'41196' b'5996' b'51224' b'811076' b'54124' b'66308'
 b'9844' b'77244' b'41604' b'92396' b'7128' b'5860' b'90068' b'71792'
 b'33724' b'3176' b'3356' b'1504' b'65564' b'41428' b'768752' b'54148'
 b'839900' b'52140' b'810996' b'13416' b'65548' b'811772' b'11752'
 b'78432' b'199836' b'452300' b'48648' b'64968' b'787256' b'67576'
 b'41768' b'6640' b'246112' b'74796' b'59128' b'41756' b'108772' b'1156'
 b'6716' b'839892' b'2596' b'49488' b'49804' b'845268' b'206252' b'26792'
 b'110564' b'9568' b'41224' b'603460' b'65464' b'41724' b'185620' b'88576'
 b'88740' b'10920' b'70176' b'377356' b'811428' b'8168' b'149008' b'49388'
 b'12872' b'65144' b'33652' b'151976' b'49816' b'48012' b'14468' b'4744'
 b'6832' b'33644' b'41432' b'71260' b'214460' b'605148' b'41204' b'816568'
 b'77516' b'8244']
Feature: top_1_7_day_non_fresh_product
Tensor: [b'2192' b'124' b'1352' b'1356' b'1228' b'968504' b'8216' b'7424' b'1528'
 b'736296' b'245488' b'67624' b'51504' b'5616' b'59608' b'88' b'9956'
 b'40456' b'1332' b'2496' b'64616' b'3460' b'66460' b'11424' b'80460'
 b'2556' b'8500' b'10104' b'455536' b'1380' b'399060' b'19740' b'1276'
 b'4648' b'16696' b'37752' b'5344' b'28' b'1232' b'1560' b'2492' b'1184'
 b'45244' b'2572' b'771148' b'2412' b'60928' b'24' b'2860' b'NA' b'1516'
 b'4708' b'211568' b'2140' b'12672' b'1284' b'44796' b'2732' b'31068'
 b'1240' b'1424' b'1324' b'1452' b'4408' b'116796' b'2676' b'7152' b'3060'
 b'809012' b'14828' b'7108' b'64088' b'20' b'455204' b'48688' b'4748'
 b'36584' b'53648' b'118652' b'313612' b'210984' b'8388' b'3056' b'2188'
 b'4696' b'16600' b'1304' b'2776' b'25136' b'36328' b'75152' b'6348'
 b'57152' b'6156' b'25128' b'300016' b'1344' b'92344' b'8104' b'70340'
 b'6564' b'25108' b'70516' b'1328' b'7668' b'36568' b'1220' b'7224'
 b'8592' b'4104' b'3124' b'2132' b'116452' b'4328' b'3808' b'24816'
 b'915816' b'135372' b'51292' b'277808' b'49712' b'160' b'50552' b'2296'
 b'326180' b'16680' b'3532' b'2704' b'4160' b'583488' b'6356' b'1512'
 b'370204' b'4464' b'3976' b'3488' b'2488' b'6364' b'3596' b'1312'
 b'36504' b'818192' b'50636' b'4948' b'2568' b'2584' b'108' b'4564'
 b'84160' b'10756' b'65932' b'48664' b'2456' b'4924' b'12552' b'5388'
 b'490528' b'5672' b'70292' b'65812' b'3092' b'84652' b'956856' b'32'
 b'3200' b'2416' b'10808' b'51448' b'8556' b'41872' b'90236' b'557064'
 b'1216' b'447028' b'75124' b'84372' b'3236' b'3744' b'65428' b'1248'
 b'66564' b'9416' b'147824' b'32856' b'12136' b'2260' b'293556' b'11632'
 b'33180' b'33412' b'49756' b'90296' b'4016' b'4780' b'2552' b'3668'
 b'764628' b'26508' b'6944' b'1500' b'16668' b'3276' b'5596' b'45612'
 b'7176' b'216276' b'63380' b'5080' b'6612' b'95460' b'44480' b'74684'
 b'219788' b'7980' b'6052' b'11008' b'64228' b'25132' b'2112' b'2148'
 b'12556' b'4816' b'36444' b'15604' b'2240' b'95320' b'51864' b'3920'
 b'450356' b'989708' b'11836' b'77380' b'9544' b'957296' b'11732' b'10200'
 b'557748' b'908208' b'77908' b'57148' b'28376' b'168' b'103520' b'36852'
 b'14796' b'3784' b'1404' b'94716' b'103884' b'84' b'4196' b'251808' b'72'
 b'51620' b'92284' b'24980' b'4812' b'60944' b'2508' b'2256' b'9884'
 b'3484' b'83740' b'3720' b'7736' b'501784' b'83872' b'6512' b'776584'
 b'76' b'14480' b'136' b'961820' b'4192' b'6212' b'2280' b'64824' b'12204'
 b'16168' b'6748' b'3468' b'1360' b'113520' b'12532' b'10428' b'765808'
 b'8704' b'12176' b'4704' b'89560' b'62252' b'11432' b'7960' b'6664'
 b'5444' b'142452' b'5636' b'3144' b'5944' b'2688' b'1224' b'24836'
 b'3564' b'6380' b'17784' b'15920' b'3344' b'5688' b'2348' b'2208'
 b'51556' b'114072' b'68460' b'17528' b'3324' b'1552' b'17596' b'119164'
 b'65424' b'48608' b'8644' b'597344' b'65968' b'903488' b'12436' b'1252'
 b'3736' b'1368' b'52220' b'2848' b'95916' b'92164' b'65012' b'12544'
 b'7228' b'73408' b'2332' b'214472' b'77936' b'286488' b'68' b'31060'
 b'989268' b'1384' b'13636' b'373576' b'121212' b'1212' b'455356' b'44860'
 b'5508' b'40396' b'7712' b'2268' b'379780' b'3028' b'5404' b'14524'
 b'2304' b'24112' b'1556' b'65696' b'97332' b'6632' b'6816' b'10424'
 b'4880' b'33276' b'87020' b'5704' b'200112' b'273364' b'54988' b'454264'
 b'113336' b'6072' b'24932' b'96944' b'9132' b'2264' b'83596' b'64112'
 b'4520' b'1256' b'2248' b'6524' b'38512' b'22320' b'2520' b'25384'
 b'55156' b'2180' b'11052' b'8808' b'111148' b'809428' b'4560' b'5236'
 b'91612' b'306644' b'107352' b'2532']
Feature: top_2_7_day_non_fresh_product
Tensor: [b'51504' b'51716' b'65436' b'1352' b'2456' b'2492' b'1356' b'23944'
 b'2188' b'2192' b'5316' b'1764' b'4240' b'10104' b'1312' b'609960' b'124'
 b'22260' b'65932' b'2132' b'14804' b'557064' b'7668' b'57152' b'1424'
 b'8500' b'82400' b'1620' b'3600' b'28' b'1500' b'12556' b'2688' b'4816'
 b'2572' b'12176' b'2180' b'25108' b'68484' b'3668' b'2140' b'14756'
 b'17756' b'1560' b'4148' b'14764' b'2848' b'16800' b'173436' b'6668'
 b'114296' b'9344' b'2584' b'40456' b'1276' b'1512' b'6844' b'1184'
 b'3200' b'88' b'65828' b'1452' b'NA' b'149492' b'5080' b'48736' b'1360'
 b'8592' b'16132' b'44872' b'36764' b'19740' b'495964' b'31116' b'1284'
 b'4908' b'68' b'1588' b'4648' b'8216' b'1228' b'64136' b'65052' b'3092'
 b'1220' b'1612' b'7736' b'122012' b'66564' b'2520' b'6612' b'3276'
 b'3144' b'9308' b'42444' b'6348' b'2352' b'24' b'2296' b'4748' b'60856'
 b'3824' b'66088' b'44480' b'917780' b'11928' b'83900' b'10808' b'2516'
 b'968008' b'2416' b'2440' b'749928' b'11468' b'2412' b'951152' b'7108'
 b'1188' b'293556' b'68496' b'51444' b'764100' b'2148' b'4220' b'5084'
 b'399060' b'4520' b'3744' b'1272' b'596104' b'5136' b'8180' b'89028'
 b'20' b'300016' b'4524' b'10036' b'12136' b'45572' b'78504' b'2704'
 b'455536' b'98044' b'25132' b'49712' b'49732' b'3124' b'49760' b'2208'
 b'4408' b'1556' b'2176' b'28840' b'71452' b'3056' b'4276' b'5616'
 b'64680' b'61112' b'10756' b'31068' b'908208' b'4192' b'1344' b'19172'
 b'4572' b'64088' b'1368' b'6848' b'1232' b'4812' b'105632' b'56' b'2260'
 b'454264' b'36444' b'73076' b'54988' b'4000' b'4172' b'2676' b'67028'
 b'82364' b'76200' b'3084' b'1212' b'5056' b'1464' b'5348' b'65428'
 b'3516' b'2144' b'6352' b'1468' b'89688' b'36568' b'82244' b'11336'
 b'70516' b'83740' b'2860' b'3196' b'4564' b'2672' b'227156' b'8868'
 b'2508' b'12656' b'1536' b'66796' b'488608' b'25772' b'51620' b'173052'
 b'37928' b'4104' b'1404' b'2556' b'4196' b'597420' b'36852' b'12272'
 b'502228' b'65708' b'10896' b'8556' b'27232' b'11024' b'6356' b'2332'
 b'10992' b'94712' b'10064' b'11924' b'76' b'565772' b'7912' b'66460'
 b'785820' b'22160' b'184120' b'108936' b'2248' b'43932' b'8388' b'66448'
 b'14628' b'11512' b'3660' b'5960' b'6568' b'100696' b'7880' b'32'
 b'475956' b'2304' b'65816' b'66568' b'1332' b'1248' b'5704' b'80116'
 b'61064' b'823960' b'28368' b'908244' b'51292' b'65836' b'71428' b'2388'
 b'172' b'41872' b'76312' b'16600' b'2540' b'105900' b'816152' b'11236'
 b'20180' b'7224' b'12848' b'1244' b'3028' b'36824' b'21824' b'777220'
 b'12360' b'3344' b'14532' b'242756' b'51424' b'82604' b'64852' b'9956'
 b'3596' b'444016' b'5688' b'4040' b'784484' b'1436' b'9872' b'2624'
 b'12580' b'300012' b'955756' b'5116' b'3460' b'22916' b'176580' b'1324'
 b'1488' b'64056' b'4292' b'58312' b'36848' b'24984' b'42608' b'44884'
 b'988636' b'35988' b'108' b'11376' b'66956' b'5236' b'2512' b'66952'
 b'145892' b'63996' b'71440' b'761392' b'489120' b'51756' b'11200'
 b'530892' b'2484' b'43976' b'65664' b'71004' b'24816' b'40432' b'76144'
 b'1396' b'50876' b'48600' b'25128' b'5508' b'8960' b'1584' b'54976'
 b'70220' b'3236' b'10224' b'21512' b'12544' b'5636' b'10184' b'1328'
 b'57148' b'65916' b'49180' b'55380' b'7984' b'83132' b'3868' b'16536'
 b'19748' b'35452' b'964104' b'6132' b'65424' b'64824' b'916296' b'1240'
 b'108712' b'16748' b'66348' b'5444' b'12184' b'3524' b'43108' b'214408'
 b'91696' b'5232' b'11688' b'45204' b'48624' b'78848' b'43384' b'7492'
 b'7744' b'24784' b'1320' b'5592' b'51448' b'601476' b'3284' b'65684'
 b'70292' b'83460' b'9276' b'746308' b'70340' b'4936' b'4380' b'2348'
 b'375392' b'36912' b'42912' b'12380' b'93044' b'17596' b'67244' b'9544'
 b'551076' b'15920' b'2212' b'2532' b'54436' b'2732' b'4948' b'3108'
 b'750428' b'753992' b'6364' b'3476' b'144788' b'5984' b'36328' b'122672'
 b'1528' b'64664' b'1420' b'9408' b'84928' b'443368' b'24788' b'24116'
 b'5736' b'3920' b'1572' b'5676' b'203036' b'2292' b'79408' b'16' b'5332'
 b'34880' b'6156' b'8124' b'6452' b'3956' b'65812' b'279408' b'273356'
 b'537452' b'4160' b'3736' b'1460' b'737736' b'53684' b'6276' b'683160'
 b'46988' b'144' b'10892' b'1304' b'12704' b'24836' b'51752' b'65904'
 b'11880' b'3488' b'49664' b'7176' b'49448' b'3060' b'42612' b'819108'
 b'12436' b'6224' b'24940' b'120' b'49452' b'4016' b'3480' b'16696'
 b'2232']
Feature: top_3_7_day_non_fresh_product
Tensor: [b'3056' b'1284' b'86780' b'119632' b'118652' b'2624' b'2332' b'66312'
 b'2572' b'2732' b'41872' b'5736' b'1368' b'70312' b'51580' b'1312'
 b'66564' b'70516' b'1232' b'25108' b'65444' b'62080' b'965524' b'5616'
 b'1248' b'4220' b'66108' b'1352' b'6632' b'4816' b'1424' b'81096' b'2132'
 b'NA' b'24284' b'1356' b'11200' b'8500' b'54524' b'8960' b'2776' b'2492'
 b'1184' b'34580' b'5104' b'5316' b'2704' b'30292' b'12324' b'14480' b'32'
 b'1228' b'88' b'3476' b'7984' b'11924' b'3460' b'78436' b'54988' b'55048'
 b'1212' b'7816' b'108104' b'10896' b'2848' b'41864' b'77996' b'5388'
 b'7136' b'65172' b'124' b'1500' b'9884' b'1560' b'3720' b'315932' b'7152'
 b'9188' b'64596' b'8216' b'300016' b'108' b'1276' b'2192' b'2256'
 b'56896' b'51504' b'24804' b'16072' b'735820' b'538028' b'2772' b'16624'
 b'1596' b'51972' b'4192' b'82864' b'6348' b'19420' b'2496' b'94160'
 b'67364' b'29612' b'80024' b'3808' b'9432' b'2908' b'4748' b'19740'
 b'11052' b'834652' b'1344' b'583488' b'4948' b'5024' b'66476' b'64636'
 b'24816' b'6364' b'74440' b'76364' b'2260' b'40896' b'8172' b'762880'
 b'49664' b'1452' b'3236' b'102400' b'1360' b'1528' b'2520' b'2512'
 b'2540' b'951380' b'66940' b'9956' b'57616' b'274296' b'5084' b'999344'
 b'21776' b'12656' b'11220' b'3092' b'28840' b'160' b'7272' b'6032'
 b'16676' b'9200' b'3060' b'14760' b'51788' b'5360' b'2180' b'40620'
 b'14292' b'1268' b'12848' b'10448' b'4964' b'42488' b'17452' b'5080'
 b'12176' b'139840' b'83872' b'49684' b'41524' b'767708' b'2108' b'15608'
 b'8252' b'112988' b'10036' b'50848' b'6224' b'6156' b'7896' b'949800'
 b'3124' b'49672' b'139636' b'76404' b'780084' b'5244' b'2584' b'4300'
 b'66760' b'57084' b'4656' b'20' b'6356' b'2516' b'2680' b'19088'
 b'989268' b'51672' b'5624' b'10028' b'24188' b'3260' b'1240' b'1456'
 b'151936' b'51372' b'5872' b'7632' b'2412' b'2556' b'913772' b'454264'
 b'813516' b'57540' b'43024' b'2688' b'6784' b'4240' b'3596' b'64056'
 b'10428' b'65052' b'5664' b'66348' b'4700' b'3668' b'65836' b'1612'
 b'5596' b'6292' b'682264' b'10624' b'2296' b'71500' b'2588' b'4408'
 b'1244' b'6568' b'1220' b'949872' b'4704' b'3344' b'3964' b'66460'
 b'3744' b'3600' b'455536' b'2568' b'293556' b'2608' b'908208' b'2208'
 b'12136' b'42544' b'2144' b'3488' b'67624' b'81296' b'65096' b'5232'
 b'10092' b'41544' b'67704' b'7668' b'2860' b'2244' b'64664' b'1336'
 b'76708' b'67444' b'3200' b'27300' b'31068' b'8560' b'1304' b'25748'
 b'12544' b'10116' b'5332' b'48276' b'33044' b'4648' b'4164' b'27072'
 b'4196' b'73540' b'86924' b'28' b'287820' b'4104' b'91936' b'11872'
 b'117756' b'11660' b'764728' b'79408' b'2388' b'68484' b'51660' b'1584'
 b'1468' b'3144' b'6132' b'4464' b'5704' b'5076' b'56136' b'76' b'7224'
 b'3816' b'36444' b'2232' b'51752' b'11836' b'60944' b'100308' b'60856'
 b'99648' b'88064' b'65488' b'24912' b'592792' b'1200' b'12636' b'65452'
 b'1188' b'48736' b'22320' b'65524' b'5508' b'35772' b'2488' b'191112'
 b'2136' b'587804' b'7492' b'234828' b'25116' b'5312' b'561804' b'6452'
 b'7436' b'48412' b'5344' b'4988' b'14524' b'2148' b'21336' b'6380'
 b'6664' b'55000' b'13824' b'7720' b'68' b'55064' b'5464' b'365544'
 b'9628' b'68304' b'8384' b'51292' b'5004' b'16264' b'184120' b'4112'
 b'64888' b'67508' b'3228' b'65828' b'561488' b'682952' b'47852' b'66796'
 b'60444' b'12204' b'67976' b'41040' b'2504' b'33276' b'75928' b'95320'
 b'215712' b'65016' b'234124' b'51564' b'60940' b'16536' b'65932' b'4036'
 b'8600' b'344412' b'9780' b'80216' b'65872' b'54520' b'233732' b'8592'
 b'8488' b'2416' b'36504' b'84144' b'5228' b'96776' b'65824' b'10808'
 b'63996' b'10348' b'21912' b'4480' b'2696' b'24916' b'9320' b'5636'
 b'767868' b'12056' b'25772' b'908212' b'400992' b'23988' b'24792' b'4152'
 b'7068' b'89756' b'2352' b'16652' b'946776' b'6204' b'2524' b'4328'
 b'66700' b'8300' b'2348' b'82836' b'18448' b'465656' b'125324' b'7532'
 b'9504' b'3660' b'40584' b'36' b'25784' b'74916' b'49756' b'955768'
 b'81828' b'582564' b'1320' b'965600' b'3796' b'12716' b'601476' b'17436'
 b'6848' b'22100' b'2140' b'25684' b'10104' b'42876' b'63016' b'34600'
 b'55228' b'30816' b'67552' b'44412' b'6212' b'64748' b'5444' b'2152'
 b'5960' b'9408' b'14764' b'20812' b'21944' b'59332' b'2864' b'3700'
 b'3096' b'1572' b'55332' b'187560' b'51840' b'48408' b'9908' b'12404'
 b'7108' b'3880' b'444016' b'49552' b'12360' b'4936' b'55172' b'71128'
 b'44588' b'9496' b'8204' b'87196' b'86380' b'2460' b'547432' b'51444'
 b'606420' b'1548' b'170900' b'108972' b'78032' b'51756' b'108812'
 b'11976' b'4520' b'23408' b'75124' b'528252' b'295104' b'59624' b'12200'
 b'9360' b'4172' b'60752' b'1556' b'1552' b'739472' b'6952' b'97408'
 b'1224' b'4276' b'71148' b'5184' b'1324' b'4176']
Feature: top_4_7_day_non_fresh_product
Tensor: [b'51444' b'5056' b'2624' b'1500' b'88' b'55128' b'10260' b'79604'
 b'65932' b'3200' b'51504' b'6380' b'5344' b'3056' b'64824' b'2412'
 b'1356' b'1464' b'66460' b'1424' b'83740' b'65336' b'14760' b'1244'
 b'124' b'2280' b'7080' b'300016' b'36584' b'41548' b'28' b'16696' b'NA'
 b'36836' b'1452' b'4116' b'99648' b'49676' b'50876' b'12056' b'4408'
 b'2416' b'62732' b'2492' b'7876' b'38164' b'5080' b'7108' b'57164'
 b'51348' b'173052' b'5636' b'1232' b'1228' b'37752' b'10428' b'2556'
 b'5736' b'122680' b'118652' b'97792' b'8388' b'2192' b'142952' b'3464'
 b'1312' b'40360' b'65428' b'12668' b'17596' b'7736' b'4816' b'1368'
 b'2572' b'11168' b'3660' b'12136' b'40412' b'7224' b'10036' b'10756'
 b'682264' b'1304' b'175588' b'28368' b'2672' b'2296' b'57152' b'66564'
 b'2332' b'16224' b'24788' b'5920' b'2408' b'1184' b'749048' b'1344'
 b'5228' b'67508' b'4696' b'175948' b'2460' b'27208' b'1284' b'2732'
 b'24836' b'85296' b'4560' b'34880' b'3124' b'914476' b'4948' b'11884'
 b'3120' b'3808' b'23012' b'17756' b'5992' b'9456' b'2132' b'1276' b'1560'
 b'771140' b'1240' b'6348' b'8252' b'300012' b'84720' b'38148' b'68372'
 b'4196' b'14756' b'2512' b'958324' b'11664' b'97408' b'66108' b'11924'
 b'5704' b'2352' b'105744' b'22308' b'3744' b'64828' b'3100' b'11224'
 b'1352' b'71188' b'450748' b'90708' b'51372' b'36444' b'9344' b'66492'
 b'2704' b'7984' b'6156' b'9924' b'1404' b'14524' b'6452' b'3084' b'3484'
 b'55532' b'5624' b'32920' b'37916' b'1324' b'15944' b'21912' b'5688'
 b'14480' b'905692' b'721788' b'16536' b'64088' b'2676' b'62252' b'8592'
 b'562740' b'24896' b'52536' b'65888' b'7816' b'464592' b'8216' b'5000'
 b'3392' b'3276' b'51972' b'583288' b'11944' b'15816' b'2180' b'3144'
 b'5576' b'743952' b'68560' b'120872' b'949656' b'14764' b'9628' b'105900'
 b'65424' b'48952' b'74916' b'11424' b'7492' b'55348' b'3196' b'2568'
 b'35440' b'8920' b'3920' b'2532' b'10412' b'110196' b'84160' b'3596'
 b'6072' b'2188' b'106840' b'48408' b'62636' b'8500' b'58920' b'2144'
 b'462960' b'2776' b'2456' b'110144' b'15920' b'449588' b'7500' b'4800'
 b'6032' b'5084' b'24' b'4520' b'2848' b'1248' b'103984' b'24912' b'6356'
 b'8408' b'12096' b'41512' b'24000' b'5116' b'3108' b'12544' b'16456'
 b'28356' b'3060' b'565168' b'2868' b'7436' b'1516' b'10808' b'12176'
 b'68028' b'116' b'111608' b'3024' b'749300' b'15228' b'38160' b'1280'
 b'11976' b'5136' b'108' b'64636' b'9504' b'66204' b'64888' b'53688'
 b'50552' b'1027164' b'54044' b'56592' b'3460' b'4364' b'94812' b'196'
 b'41496' b'22232' b'1220' b'7572' b'10092' b'4192' b'56468' b'19172'
 b'2588' b'3616' b'11848' b'913772' b'22208' b'732280' b'4692' b'4700'
 b'5444' b'2908' b'4936' b'95160' b'948188' b'953008' b'10564' b'57116'
 b'489216' b'45572' b'2252' b'80880' b'74700' b'28344' b'2440' b'59300'
 b'4484' b'36312' b'43528' b'118412' b'7704' b'10104' b'5776' b'68484'
 b'2860' b'2584' b'6456' b'45204' b'12704' b'4172' b'912528' b'68'
 b'65496' b'603544' b'36848' b'2108' b'955216' b'4488' b'36488' b'82836'
 b'84652' b'42168' b'6364' b'76' b'2772' b'4924' b'78208' b'1556' b'45080'
 b'1272' b'394232' b'41516' b'48600' b'10596' b'7608' b'12012' b'48704'
 b'23988' b'25684' b'11200' b'66448' b'22476' b'88224' b'9408' b'64468'
 b'175644' b'1212' b'63996' b'31112' b'55904' b'60440' b'25128' b'466728'
 b'20264' b'20056' b'70476' b'51292' b'10896' b'54920' b'96672' b'5248'
 b'12556' b'65452' b'1320' b'5508' b'730552' b'185024' b'405768' b'12436'
 b'250384' b'5960' b'37652' b'9956' b'2508' b'95584' b'2348' b'490528'
 b'455204' b'1528' b'114356' b'62776' b'52492' b'51756' b'10384' b'3668'
 b'16236' b'81644' b'147844' b'83900' b'57024' b'1460' b'823924' b'7072'
 b'6612' b'1396' b'74788' b'196688' b'2260' b'68252' b'57244' b'67688'
 b'227660' b'37928' b'7832' b'66452' b'48348' b'64728' b'35956' b'10832'
 b'6664' b'488608' b'3468' b'14628' b'67708' b'7084' b'16800' b'41872'
 b'3600' b'6984' b'537084' b'40672' b'16144' b'211816' b'42600' b'4380'
 b'8384' b'82856' b'5312' b'79356' b'54988' b'3488' b'2488' b'2552'
 b'501788' b'91280' b'754876' b'962076' b'82320' b'9140' b'11488' b'10868'
 b'6120' b'40844' b'164' b'40248' b'75820' b'5004' b'597460' b'2520'
 b'9768' b'965604' b'9024' b'12204' b'12264' b'4356' b'63016' b'601492'
 b'21672' b'84336' b'56848' b'73408' b'32904' b'42884' b'76768' b'57556'
 b'48304' b'71004' b'8176' b'2256' b'22100' b'6288' b'6276' b'21276'
 b'5244' b'6792' b'106456' b'6104' b'80780' b'2148' b'31068' b'4760'
 b'10792' b'15652' b'3096' b'25748' b'17716' b'2112' b'187684' b'81296'
 b'77960' b'10480' b'67412' b'12412' b'112040' b'2872' b'32956' b'48852'
 b'71160' b'25696' b'79408' b'47464' b'16668' b'11432' b'12272' b'610392'
 b'331880' b'11480' b'908208' b'2484' b'588196' b'8756' b'97980' b'5464'
 b'74416' b'968940' b'454504' b'3612' b'77080' b'226108' b'73340' b'45796'
 b'70428' b'115332' b'17424' b'957504' b'448748' b'17452' b'949872'
 b'73232' b'10064' b'7412' b'776856' b'9908' b'12456' b'2304' b'68328'
 b'2176' b'41524' b'7424' b'2688' b'9224']
Feature: top_5_7_day_non_fresh_product
Tensor: [b'88' b'6212' b'65452' b'2460' b'1356' b'NA' b'14724' b'82084' b'1352'
 b'3488' b'944924' b'7272' b'100808' b'12552' b'12176' b'2572' b'2508'
 b'3144' b'2188' b'681956' b'2624' b'1516' b'989736' b'1452' b'1220'
 b'3596' b'4572' b'9780' b'1424' b'67000' b'86960' b'1312' b'2492'
 b'64252' b'54436' b'10208' b'112' b'49680' b'48664' b'571896' b'4948'
 b'2192' b'65012' b'105744' b'14760' b'44480' b'41872' b'5992' b'75124'
 b'60960' b'65288' b'1284' b'2456' b'64088' b'64100' b'16160' b'10092'
 b'300016' b'124' b'2608' b'19664' b'2412' b'4812' b'6348' b'2704'
 b'71128' b'445108' b'31112' b'51292' b'7876' b'2772' b'12324' b'4172'
 b'36828' b'92352' b'78884' b'43860' b'15608' b'11432' b'66760' b'1328'
 b'3964' b'1304' b'173416' b'2688' b'78052' b'9416' b'501788' b'25128'
 b'55128' b'52460' b'76' b'6816' b'3868' b'1276' b'2672' b'5232' b'67512'
 b'9188' b'64596' b'1252' b'41596' b'2676' b'2540' b'3744' b'3056' b'2280'
 b'2132' b'966320' b'8212' b'42484' b'1500' b'16072' b'113580' b'5080'
 b'3644' b'242756' b'3736' b'3200' b'9368' b'24584' b'37652' b'41584'
 b'6292' b'9472' b'2256' b'3720' b'4268' b'2556' b'6352' b'8444' b'57084'
 b'193816' b'14808' b'59580' b'3880' b'37936' b'5736' b'1232' b'3660'
 b'3392' b'80460' b'908208' b'146088' b'9504' b'3808' b'108104' b'4040'
 b'65060' b'3468' b'51304' b'66476' b'843404' b'60440' b'55396' b'36848'
 b'53688' b'74416' b'10276' b'106456' b'11024' b'8048' b'7560' b'10412'
 b'3028' b'7140' b'66460' b'24228' b'8500' b'8216' b'71120' b'9956'
 b'60456' b'4408' b'9884' b'65096' b'7716' b'3668' b'5988' b'54508'
 b'2296' b'28376' b'65248' b'66376' b'363420' b'14732' b'557064' b'65260'
 b'68500' b'64824' b'10892' b'48408' b'60856' b'14376' b'5476' b'4192'
 b'12516' b'20752' b'3124' b'23176' b'12636' b'6240' b'1416' b'1228'
 b'73232' b'40396' b'10756' b'406932' b'70544' b'2524' b'59840' b'173052'
 b'9792' b'399060' b'67988' b'10480' b'35448' b'49164' b'3436' b'2872'
 b'6612' b'65836' b'27208' b'60388' b'110200' b'761164' b'4196' b'17756'
 b'2632' b'176976' b'51568' b'120872' b'9436' b'817352' b'6512' b'8768'
 b'3096' b'80508' b'823924' b'3060' b'36764' b'450340' b'18152' b'4540'
 b'7548' b'10616' b'3092' b'6568' b'60708' b'5184' b'8408' b'13520'
 b'16732' b'1404' b'66040' b'12260' b'4104' b'115616' b'65824' b'25108'
 b'86116' b'81328' b'7712' b'3516' b'764028' b'3344' b'8868' b'2440'
 b'51504' b'17436' b'3700' b'1280' b'70744' b'537168' b'3564' b'80776'
 b'42076' b'35520' b'2512' b'8556' b'4240' b'2588' b'107352' b'71428'
 b'183896' b'88168' b'65492' b'54456' b'65828' b'12360' b'4148' b'7736'
 b'5056' b'6452' b'15920' b'2516' b'250384' b'2464' b'42488' b'36836'
 b'64084' b'11000' b'48412' b'77848' b'10808' b'44492' b'2732' b'57152'
 b'64616' b'1560' b'5576' b'6276' b'5700' b'9324' b'4524' b'6188' b'1256'
 b'64056' b'3920' b'550912' b'80536' b'70820' b'90404' b'19172' b'78308'
 b'7936' b'5308' b'120' b'65428' b'2520' b'7224' b'68512' b'20000'
 b'56584' b'45248' b'176164' b'26404' b'11848' b'24940' b'775664' b'5008'
 b'213436' b'10420' b'7764' b'28652' b'104' b'4564' b'3476' b'3480'
 b'949832' b'4960' b'51444' b'3444' b'454264' b'227660' b'6156' b'64680'
 b'147844' b'42176' b'9680' b'60944' b'2776' b'21668' b'105428' b'586936'
 b'36312' b'79536' b'49536' b'77892' b'70624' b'2292' b'12056' b'46036'
 b'65932' b'205884' b'160' b'5704' b'44412' b'35240' b'84488' b'16696'
 b'3032' b'65916' b'24816' b'54524' b'17196' b'10320' b'84016' b'5116'
 b'66680' b'601476' b'51676' b'45612' b'66564' b'7424' b'89136' b'821476'
 b'26628' b'12780' b'67704' b'60556' b'1324' b'2112' b'303504' b'28608'
 b'68316' b'51584' b'7984' b'5228' b'102292' b'5652' b'2304' b'6132'
 b'732280' b'99288' b'70368' b'70516' b'28404' b'22204' b'183168' b'8600'
 b'91936' b'488608' b'2860' b'4164' b'8452' b'3108' b'10428' b'86348'
 b'595828' b'9360' b'3824' b'5332' b'70332' b'78092' b'442208' b'76764'
 b'9868' b'188248' b'51752' b'75160' b'76816' b'42336' b'12556' b'16544'
 b'2584' b'7744' b'6204' b'33276' b'70784' b'207048' b'65860' b'22288'
 b'2956' b'1224' b'40680' b'65804' b'5136' b'28348' b'65432' b'8384'
 b'2108' b'4816' b'1512' b'473168' b'14480' b'11560' b'5924' b'55620'
 b'956856' b'113544' b'842888' b'125220' b'34600' b'16272' b'56460'
 b'1568' b'3276' b'83872' b'7072' b'7584' b'70364' b'15952' b'17452'
 b'15960' b'5244' b'68560' b'27212' b'9040' b'40636' b'49448' b'947460'
 b'609960' b'2348' b'64000' b'105900' b'64228' b'66108' b'57760' b'70888'
 b'6068' b'92472' b'78408' b'7528' b'9756' b'41516' b'10028' b'7108'
 b'11160' b'66312' b'136' b'5596' b'8064' b'68460' b'4520' b'76412'
 b'62080' b'4700' b'436632' b'97408' b'3976' b'66016' b'614084' b'5032'
 b'5508' b'421128' b'108296' b'74700' b'44404' b'551076' b'757168' b'5240'
 b'695320' b'28700' b'66304' b'88064' b'1548' b'47592' b'26356' b'36444'
 b'22356' b'450748' b'9820' b'11696' b'13884' b'7436' b'737940' b'12088'
 b'573900' b'990568' b'9408' b'832488' b'147112' b'94460' b'36568'
 b'74640' b'176692' b'43712' b'42392' b'960788' b'113312' b'2260' b'52000'
 b'17680' b'32832' b'8896' b'103080' b'74440' b'3460' b'4160' b'12656'
 b'103300' b'9600' b'5076' b'192600' b'50644' b'2708' b'105184' b'12676'
 b'65688' b'36580' b'5616' b'10684']
Feature: top_1_15_day_non_fresh_product
Tensor: [b'2192' b'124' b'1352' b'1356' b'2456' b'968504' b'82084' b'2188'
 b'956856' b'1528' b'736296' b'245488' b'67624' b'51504' b'2132' b'4172'
 b'557064' b'88' b'57152' b'9140' b'97792' b'2496' b'64616' b'3600'
 b'1312' b'1500' b'66460' b'11424' b'54436' b'10208' b'8500' b'10104'
 b'1380' b'1184' b'399060' b'1276' b'4648' b'16696' b'17756' b'5344'
 b'1560' b'1232' b'14764' b'2492' b'108104' b'45244' b'2572' b'771148'
 b'1228' b'2412' b'60928' b'24' b'28' b'813520' b'1516' b'8592' b'2140'
 b'12672' b'49552' b'44796' b'2732' b'31068' b'565672' b'1424' b'1324'
 b'1452' b'4408' b'11664' b'54316' b'41548' b'809012' b'14828' b'7108'
 b'64088' b'20' b'455204' b'52652' b'48688' b'7736' b'53648' b'2520'
 b'3200' b'64252' b'66476' b'8388' b'53032' b'6364' b'7152' b'44480'
 b'36328' b'8172' b'6348' b'25128' b'300016' b'92344' b'1284' b'8104'
 b'65932' b'6564' b'25108' b'70516' b'1328' b'7668' b'764100' b'7224'
 b'150304' b'6032' b'116452' b'4328' b'3808' b'1272' b'2352' b'24816'
 b'3276' b'277808' b'1304' b'10808' b'12136' b'22320' b'83872' b'326180'
 b'14628' b'193816' b'959932' b'3532' b'9956' b'2704' b'8252' b'65904'
 b'278172' b'583488' b'2256' b'370204' b'4464' b'3976' b'3488' b'743952'
 b'61112' b'10756' b'209364' b'74916' b'55348' b'3196' b'51292' b'3880'
 b'4816' b'56' b'1332' b'818192' b'2260' b'4948' b'2568' b'2584' b'108'
 b'4564' b'6568' b'84160' b'5348' b'12552' b'3668' b'490528' b'5672'
 b'70292' b'65812' b'3092' b'84652' b'2416' b'3344' b'51448' b'41872'
 b'1216' b'455536' b'447028' b'488608' b'84372' b'3236' b'5240' b'3744'
 b'65428' b'66564' b'173052' b'9416' b'13680' b'147824' b'36504' b'502228'
 b'2556' b'65096' b'293556' b'160' b'11632' b'33180' b'49756' b'90296'
 b'3460' b'4780' b'41864' b'785820' b'22160' b'5576' b'5444' b'96600'
 b'27072' b'3144' b'1512' b'216276' b'26404' b'597840' b'80536' b'2676'
 b'6612' b'36568' b'95460' b'68196' b'219788' b'7980' b'5076' b'982088'
 b'64228' b'37684' b'25132' b'2148' b'12556' b'16600' b'11236' b'2860'
 b'164' b'3920' b'989708' b'48736' b'577000' b'77380' b'9544' b'957296'
 b'11732' b'539436' b'557748' b'908208' b'77908' b'4160' b'5080' b'168'
 b'581988' b'592792' b'103520' b'8384' b'63120' b'84' b'10896' b'89136'
 b'72' b'24980' b'18196' b'4812' b'3056' b'60944' b'2508' b'9884' b'3484'
 b'83740' b'3720' b'501784' b'28200' b'776584' b'1240' b'14480' b'1404'
 b'4192' b'6212' b'2280' b'64824' b'12204' b'24836' b'1456' b'1360'
 b'1548' b'9344' b'113520' b'12532' b'10428' b'65828' b'12176' b'54976'
 b'11944' b'2112' b'6664' b'6156' b'68304' b'142452' b'5636' b'57148'
 b'1224' b'3564' b'65916' b'5136' b'5688' b'42600' b'5616' b'2208'
 b'51556' b'12544' b'114072' b'16748' b'17528' b'12184' b'66796' b'11560'
 b'119164' b'91696' b'6104' b'51716' b'11488' b'597344' b'147572' b'12436'
 b'1252' b'3124' b'1368' b'52220' b'7584' b'1268' b'7492' b'95916'
 b'92164' b'32' b'65012' b'42912' b'73408' b'17596' b'76' b'77936'
 b'18948' b'68' b'44412' b'989268' b'9756' b'4104' b'373576' b'121212'
 b'753992' b'99648' b'1212' b'455356' b'44860' b'9012' b'7712' b'2268'
 b'379780' b'3028' b'5404' b'2304' b'24112' b'5736' b'11848' b'65696'
 b'97332' b'7896' b'444016' b'10424' b'12360' b'33276' b'6452' b'414468'
 b'71128' b'87020' b'2296' b'54988' b'454264' b'6072' b'9040' b'573900'
 b'1460' b'96944' b'2288' b'2264' b'83596' b'64112' b'60904' b'4520'
 b'6524' b'45796' b'3516' b'448748' b'782776' b'55156' b'37752' b'49448'
 b'8808' b'819108' b'809428' b'4560' b'6224' b'5236' b'48408' b'3736'
 b'65288' b'306644' b'10320' b'2532' b'7424' b'2244']
Feature: top_2_15_day_non_fresh_product
Tensor: [b'51504' b'51716' b'65436' b'1352' b'1228' b'2492' b'1356' b'41552'
 b'5844' b'1764' b'4240' b'10104' b'1312' b'609960' b'124' b'66564'
 b'70516' b'2188' b'66460' b'7668' b'62080' b'1424' b'88' b'8500' b'1284'
 b'1332' b'835436' b'60904' b'81096' b'1500' b'12556' b'80460' b'4816'
 b'2572' b'12176' b'8960' b'6348' b'25108' b'2416' b'3668' b'41872'
 b'14756' b'37752' b'28' b'4196' b'300012' b'1560' b'3460' b'97792'
 b'173436' b'36824' b'1184' b'142952' b'5988' b'40456' b'1276' b'74704'
 b'31112' b'60856' b'65828' b'2860' b'2584' b'3720' b'66088' b'2280'
 b'5240' b'64596' b'10756' b'300016' b'12204' b'482992' b'3200' b'2296'
 b'44872' b'503952' b'24804' b'565592' b'65688' b'3344' b'78672' b'16624'
 b'2676' b'7152' b'70784' b'2456' b'82864' b'19664' b'2132' b'1620'
 b'65052' b'3092' b'2192' b'4748' b'6612' b'118652' b'210984' b'5992'
 b'67412' b'57152' b'32' b'3056' b'2352' b'1240' b'4692' b'66476' b'16600'
 b'1304' b'917780' b'40896' b'75152' b'6452' b'2516' b'2440' b'102400'
 b'24' b'4656' b'2412' b'3744' b'51672' b'8560' b'70340' b'7108' b'965524'
 b'31068' b'10792' b'36568' b'989584' b'10276' b'453164' b'8592' b'414180'
 b'3124' b'16676' b'4520' b'10036' b'70444' b'9040' b'135372' b'50876'
 b'1324' b'20' b'4524' b'49712' b'160' b'5688' b'50552' b'45572' b'583488'
 b'2704' b'455536' b'4408' b'49732' b'348700' b'6356' b'2732' b'2176'
 b'4480' b'71452' b'139872' b'14764' b'4276' b'5616' b'5344' b'68560'
 b'2488' b'6364' b'1344' b'766544' b'64088' b'173052' b'1368' b'399060'
 b'455204' b'68512' b'3920' b'9036' b'105632' b'1452' b'NA' b'50636'
 b'2256' b'454264' b'36444' b'73076' b'54988' b'4172' b'67028' b'82364'
 b'76200' b'2776' b'907328' b'48664' b'2608' b'449588' b'5664' b'65428'
 b'5388' b'6352' b'65836' b'1468' b'5596' b'89688' b'51444' b'24912'
 b'81596' b'11336' b'2140' b'957420' b'8624' b'3196' b'4704' b'73268'
 b'227156' b'1232' b'8556' b'90236' b'1536' b'1456' b'66796' b'68028'
 b'4924' b'2688' b'3564' b'2144' b'115876' b'65932' b'87612' b'1420'
 b'17756' b'36852' b'12552' b'65708' b'73244' b'5736' b'2508' b'33412'
 b'49760' b'5432' b'11924' b'1220' b'5080' b'2552' b'565772' b'10808'
 b'6132' b'2540' b'59620' b'33044' b'3276' b'37552' b'18448' b'43932'
 b'54044' b'67552' b'766024' b'11512' b'153472' b'5960' b'6568' b'8064'
 b'3096' b'475956' b'2304' b'65816' b'66568' b'44480' b'5704' b'74684'
 b'61064' b'2848' b'6052' b'51292' b'3488' b'24940' b'71428' b'2672'
 b'2388' b'11344' b'123432' b'27256' b'1584' b'4564' b'816152' b'2240'
 b'7224' b'12848' b'592792' b'9188' b'450356' b'1244' b'8388' b'12360'
 b'1360' b'7716' b'10892' b'10200' b'45080' b'82604' b'83740' b'444016'
 b'561804' b'7492' b'57148' b'4040' b'48704' b'184120' b'28376' b'14524'
 b'1436' b'16696' b'3468' b'3784' b'5508' b'8424' b'365544' b'8384'
 b'103884' b'2556' b'251808' b'58312' b'36848' b'24984' b'97376' b'9956'
 b'35988' b'41040' b'10428' b'67976' b'5228' b'2512' b'2504' b'33276'
 b'7984' b'145892' b'64824' b'63996' b'6512' b'776524' b'51756' b'15920'
 b'16536' b'3596' b'530892' b'2484' b'10384' b'43976' b'71004' b'80656'
 b'6748' b'3060' b'64096' b'48600' b'233732' b'25116' b'108' b'3144'
 b'19740' b'765808' b'82836' b'89560' b'62252' b'251884' b'2168' b'10224'
 b'16236' b'5444' b'12544' b'7080' b'7856' b'10184' b'970944' b'7744'
 b'2696' b'11468' b'24916' b'51372' b'83132' b'3868' b'6380' b'6100'
 b'1256' b'964104' b'65424' b'1516' b'17104' b'68460' b'66348' b'3028'
 b'3324' b'1552' b'1280' b'17596' b'214408' b'5672' b'5232' b'8644'
 b'182520' b'85456' b'1320' b'65968' b'903488' b'11848' b'601476' b'3284'
 b'3736' b'70292' b'66620' b'9276' b'746308' b'55440' b'965600' b'4380'
 b'59580' b'48264' b'1404' b'375392' b'60444' b'6968' b'5576' b'7228'
 b'67244' b'214472' b'286488' b'84356' b'4948' b'17468' b'1272' b'13636'
 b'11424' b'10028' b'613884' b'612080' b'144788' b'59332' b'9224'
 b'193264' b'11432' b'64664' b'9408' b'24788' b'24116' b'6032' b'1572'
 b'5676' b'203036' b'74916' b'6816' b'24640' b'16' b'724144' b'8124'
 b'3956' b'65812' b'8920' b'200112' b'273364' b'51284' b'749048' b'4160'
 b'24932' b'170900' b'737736' b'9132' b'6276' b'683160' b'48556' b'957816'
 b'502356' b'24836' b'4956' b'65904' b'31116' b'2260' b'49664' b'234984'
 b'11052' b'20984' b'913732' b'12436' b'1224' b'557344' b'91612' b'4812'
 b'4016' b'107352' b'14584' b'2112']
Feature: top_3_15_day_non_fresh_product
Tensor: [b'88' b'1284' b'65452' b'119632' b'118652' b'2624' b'1352' b'76' b'2572'
 b'7424' b'3488' b'66088' b'70312' b'51580' b'1312' b'2508' b'65932'
 b'1228' b'94472' b'65444' b'59608' b'66564' b'65336' b'14760' b'1244'
 b'5616' b'2732' b'1620' b'66108' b'1424' b'108948' b'1356' b'1232'
 b'2488' b'949352' b'2556' b'11200' b'8500' b'54524' b'455536' b'2132'
 b'19740' b'62732' b'1368' b'5316' b'14764' b'2704' b'173052' b'32'
 b'9376' b'6452' b'590676' b'5312' b'65428' b'4564' b'78436' b'55048'
 b'4948' b'3108' b'114296' b'9344' b'6348' b'41864' b'77996' b'24816'
 b'1512' b'6844' b'1184' b'3200' b'124' b'1500' b'11168' b'1560' b'1404'
 b'19068' b'3056' b'67216' b'5080' b'11432' b'293556' b'16132' b'86780'
 b'5812' b'2688' b'56896' b'16800' b'NA' b'6816' b'538028' b'2772' b'3736'
 b'61220' b'51784' b'27296' b'331880' b'1240' b'64596' b'7224' b'2492'
 b'3744' b'51504' b'1220' b'1452' b'300016' b'80024' b'550912' b'9432'
 b'36584' b'82836' b'7720' b'1344' b'583488' b'24' b'4696' b'300012'
 b'64636' b'57084' b'60856' b'41872' b'56592' b'59580' b'25136' b'74700'
 b'57152' b'42424' b'2348' b'1276' b'94160' b'146088' b'749928' b'10296'
 b'2520' b'56472' b'1304' b'11224' b'24836' b'2140' b'3144' b'68496'
 b'3392' b'51444' b'73276' b'12336' b'2148' b'160' b'548824' b'171184'
 b'10412' b'7108' b'399060' b'5100' b'28' b'596104' b'40456' b'1332'
 b'2192' b'81096' b'32920' b'57116' b'4964' b'10036' b'9036' b'68484'
 b'613884' b'49684' b'25132' b'8644' b'51372' b'4520' b'14732' b'112988'
 b'3336' b'14524' b'2332' b'2208' b'2172' b'7896' b'78876' b'4408' b'3124'
 b'5184' b'76404' b'5244' b'2584' b'7492' b'64680' b'31068' b'909888'
 b'2456' b'4572' b'989268' b'5624' b'964960' b'45440' b'76808' b'65892'
 b'151936' b'20' b'5872' b'786164' b'761164' b'4816' b'454264' b'4000'
 b'43024' b'9436' b'3564' b'2392' b'3084' b'68304' b'2412' b'52004'
 b'7712' b'10428' b'450340' b'7500' b'65436' b'6568' b'7608' b'5084'
 b'12324' b'1612' b'5596' b'682264' b'82464' b'82244' b'11800' b'2588'
 b'70516' b'83740' b'15840' b'4704' b'948284' b'97792' b'2676' b'8868'
 b'12656' b'2568' b'328828' b'66460' b'75124' b'25772' b'9544' b'2608'
 b'7736' b'908208' b'1248' b'3476' b'11768' b'4700' b'32856' b'76588'
 b'104868' b'5028' b'10092' b'2516' b'7668' b'2244' b'64664' b'2672'
 b'54988' b'10992' b'67444' b'3480' b'10064' b'4016' b'6632' b'4196'
 b'80460' b'64952' b'4148' b'2872' b'488872' b'8216' b'5344' b'557064'
 b'16668' b'6156' b'64088' b'16536' b'45612' b'4936' b'66448' b'91936'
 b'11872' b'8552' b'3060' b'764728' b'2388' b'1468' b'120' b'59300'
 b'43528' b'908244' b'12176' b'555808' b'20152' b'34380' b'2352' b'24940'
 b'64004' b'557344' b'3596' b'2540' b'3092' b'105900' b'71296' b'10956'
 b'24912' b'2108' b'603544' b'12056' b'12636' b'1188' b'2860' b'8252'
 b'2256' b'5508' b'16176' b'60944' b'191112' b'2136' b'14532' b'7804'
 b'11708' b'84' b'1224' b'586936' b'9956' b'957176' b'5736' b'7436'
 b'11664' b'62860' b'21336' b'9408' b'12580' b'949668' b'168' b'5116'
 b'22916' b'3920' b'16264' b'4104' b'184120' b'12556' b'64888' b'67508'
 b'193816' b'3228' b'42608' b'37916' b'988636' b'47852' b'5388' b'405768'
 b'577092' b'5236' b'3600' b'108' b'83872' b'95320' b'71440' b'540040'
 b'489120' b'1456' b'66332' b'2848' b'961820' b'4036' b'98160' b'20880'
 b'110032' b'11924' b'145892' b'65260' b'57024' b'1212' b'8592' b'48600'
 b'4240' b'65836' b'84160' b'17756' b'5704' b'6132' b'36444' b'75696'
 b'6628' b'4248' b'51752' b'10808' b'9504' b'67688' b'10348' b'6664'
 b'488608' b'5944' b'8384' b'10892' b'33276' b'5636' b'908212' b'400992'
 b'7632' b'2912' b'52000' b'51716' b'2296' b'7068' b'180204' b'12544'
 b'916296' b'16652' b'108712' b'7880' b'5476' b'14480' b'205884' b'25696'
 b'43108' b'8300' b'7168' b'9320' b'48608' b'54976' b'43384' b'770864'
 b'4328' b'24784' b'82364' b'962268' b'51448' b'36' b'25784' b'49756'
 b'83460' b'66960' b'2524' b'74436' b'4608' b'1320' b'2152' b'65664'
 b'965604' b'3460' b'3700' b'3260' b'56848' b'496468' b'36912' b'4172'
 b'52672' b'42876' b'121728' b'40864' b'71004' b'3668' b'25108' b'551076'
 b'25128' b'777220' b'5444' b'2212' b'1384' b'64748' b'54980' b'54436'
 b'6792' b'750428' b'2180' b'5984' b'36328' b'9788' b'15652' b'4192'
 b'8080' b'3096' b'1420' b'55332' b'64100' b'443368' b'51840' b'48408'
 b'66304' b'26544' b'12404' b'5240' b'35584' b'44588' b'36824' b'8204'
 b'16600' b'5576' b'966360' b'2460' b'113336' b'828748' b'51348' b'9188'
 b'2696' b'108972' b'53684' b'46988' b'413740' b'679560' b'90296' b'49712'
 b'5004' b'528252' b'9360' b'42612' b'111148' b'739472' b'97408' b'12456'
 b'183240' b'45712' b'51868' b'1328' b'1324' b'2232' b'4176']
Feature: top_4_15_day_non_fresh_product
Tensor: [b'1284' b'2572' b'2624' b'124' b'1356' b'1424' b'31068' b'1232' b'65932'
 b'64888' b'3484' b'5736' b'5344' b'65060' b'64824' b'2412' b'88' b'1452'
 b'537340' b'66476' b'17756' b'1220' b'211816' b'12556' b'40456' b'2192'
 b'300016' b'66460' b'3460' b'4816' b'2492' b'64748' b'5464' b'1560'
 b'565660' b'2608' b'99648' b'54980' b'50876' b'1276' b'65140' b'68484'
 b'7108' b'38164' b'5992' b'3428' b'12324' b'1352' b'3344' b'61448'
 b'1228' b'7984' b'11924' b'122680' b'24' b'63120' b'3744' b'24816'
 b'10896' b'79752' b'1312' b'2860' b'65436' b'2144' b'4148' b'7136'
 b'65172' b'108104' b'9884' b'40412' b'140912' b'3880' b'7152' b'48736'
 b'4708' b'211568' b'453788' b'9040' b'16600' b'57152' b'98044' b'14732'
 b'1240' b'19740' b'NA' b'13860' b'2408' b'4948' b'66348' b'70888'
 b'64088' b'6276' b'1332' b'34664' b'53032' b'19420' b'2496' b'3056'
 b'12176' b'4284' b'450748' b'4648' b'3124' b'914476' b'11804' b'9672'
 b'7528' b'10428' b'313612' b'9308' b'7336' b'834652' b'9456' b'2256'
 b'14584' b'771140' b'4748' b'1436' b'74440' b'544116' b'1256' b'66088'
 b'76364' b'2260' b'4464' b'62080' b'3092' b'5136' b'100292' b'2416'
 b'1360' b'11468' b'12204' b'22308' b'2180' b'2332' b'7424' b'4172'
 b'3824' b'170036' b'57616' b'274296' b'5084' b'1500' b'12656' b'2552'
 b'28840' b'2132' b'4104' b'56' b'14760' b'51788' b'2140' b'2540'
 b'915816' b'40620' b'356280' b'573728' b'65096' b'84720' b'1456' b'5080'
 b'9376' b'16236' b'71428' b'34640' b'28' b'1324' b'12544' b'41524'
 b'8680' b'63016' b'15608' b'562740' b'5132' b'52536' b'10104' b'3200'
 b'464592' b'60856' b'1556' b'496796' b'3276' b'8388' b'756752' b'36444'
 b'6348' b'3144' b'108' b'66760' b'64636' b'2504' b'10488' b'4656'
 b'908208' b'3596' b'2516' b'19172' b'9384' b'41552' b'11424' b'7492'
 b'8500' b'8880' b'588416' b'3468' b'93884' b'3392' b'9956' b'331880'
 b'51504' b'2352' b'65016' b'5116' b'56460' b'48408' b'2704' b'10724'
 b'1184' b'4240' b'3644' b'1212' b'342536' b'52316' b'7980' b'12096'
 b'3060' b'2508' b'9140' b'966360' b'20' b'2848' b'45124' b'1572' b'6292'
 b'10624' b'150100' b'6568' b'38452' b'5228' b'4936' b'1244' b'42084'
 b'2772' b'4564' b'3964' b'7632' b'2868' b'5232' b'8868' b'1516' b'293556'
 b'71484' b'4192' b'8552' b'436864' b'66564' b'4408' b'43196' b'11976'
 b'5616' b'51292' b'3488' b'9504' b'7224' b'53688' b'11024' b'14480'
 b'4364' b'2676' b'61112' b'557344' b'56076' b'955216' b'11220' b'7572'
 b'5248' b'610036' b'10792' b'6820' b'764628' b'68204' b'26508' b'90340'
 b'2732' b'5332' b'965524' b'24980' b'5636' b'51716' b'16544' b'765204'
 b'2908' b'7176' b'24836' b'73540' b'86924' b'2348' b'64056' b'2212'
 b'57116' b'160' b'21152' b'70820' b'74700' b'51660' b'1584' b'5688'
 b'14828' b'68512' b'4380' b'823960' b'44416' b'51484' b'51304' b'3236'
 b'11664' b'2588' b'172' b'51372' b'4036' b'100308' b'6356' b'10036'
 b'3480' b'20180' b'88064' b'44992' b'65428' b'2208' b'57644' b'2512'
 b'16128' b'25132' b'2108' b'3028' b'6156' b'16696' b'82836' b'65012'
 b'762820' b'2188' b'4924' b'41512' b'51424' b'14500' b'587804' b'244148'
 b'5312' b'6212' b'8592' b'6452' b'12012' b'749048' b'4988' b'2900'
 b'8384' b'22476' b'9872' b'48900' b'6664' b'17436' b'955756' b'8920'
 b'2568' b'7668' b'79408' b'28888' b'2440' b'8768' b'54232' b'4196'
 b'8300' b'908236' b'8644' b'54920' b'3600' b'16456' b'65452' b'92284'
 b'2456' b'5508' b'561488' b'44884' b'185024' b'65836' b'12532' b'956556'
 b'66956' b'6132' b'41040' b'51584' b'66952' b'75928' b'95584' b'215712'
 b'759628' b'581988' b'4520' b'79924' b'136' b'11200' b'87020' b'1404'
 b'65664' b'169984' b'16168' b'488608' b'76144' b'36568' b'80948'
 b'121688' b'25128' b'47936' b'7072' b'551012' b'74788' b'1464' b'56624'
 b'2384' b'38056' b'8348' b'4508' b'514072' b'25772' b'32' b'10832'
 b'1328' b'682264' b'786928' b'49180' b'67708' b'7084' b'6668' b'16800'
 b'777268' b'537084' b'23988' b'12456' b'11428' b'55904' b'13632' b'16676'
 b'50668' b'408220' b'24284' b'329244' b'6204' b'2524' b'57148' b'3524'
 b'26808' b'5704' b'48424' b'54988' b'12112' b'42460' b'33276' b'11688'
 b'45204' b'48624' b'78848' b'60944' b'65972' b'3660' b'577232' b'2460'
 b'83740' b'5592' b'70516' b'164' b'3808' b'5056' b'86140' b'66992'
 b'4700' b'81828' b'60436' b'2872' b'10808' b'3668' b'12264' b'2296'
 b'22100' b'4276' b'79384' b'42884' b'946780' b'24788' b'12380' b'73248'
 b'22532' b'31060' b'15920' b'756964' b'430392' b'7532' b'3108' b'2248'
 b'5944' b'10224' b'2148' b'4760' b'21944' b'809012' b'33920' b'16136'
 b'40360' b'84928' b'82364' b'81296' b'77960' b'234900' b'51448' b'67412'
 b'12412' b'48852' b'70648' b'4880' b'9368' b'47464' b'12272' b'87196'
 b'65812' b'731448' b'65488' b'86380' b'7608' b'2484' b'537452' b'97980'
 b'606420' b'454504' b'78032' b'21704' b'108812' b'68' b'91936' b'149236'
 b'5008' b'957504' b'17452' b'66684' b'4328' b'68500' b'32836' b'7412'
 b'4696' b'60752' b'1552' b'776856' b'1344' b'485780' b'6364' b'49452'
 b'363512' b'2176' b'71148' b'49708' b'9224']
Feature: top_5_15_day_non_fresh_product
Tensor: [b'2732' b'5056' b'1424' b'1500' b'124' b'63116' b'2456' b'1352' b'2192'
 b'5316' b'6380' b'1368' b'12552' b'2332' b'88' b'22260' b'8500' b'60940'
 b'1600' b'1212' b'36488' b'1452' b'2144' b'965524' b'3596' b'19124'
 b'2488' b'300012' b'6632' b'5344' b'2624' b'2516' b'25128' b'2412'
 b'565772' b'66564' b'4116' b'16536' b'544116' b'23992' b'2304' b'2492'
 b'34580' b'99648' b'41872' b'1284' b'75124' b'30292' b'51348' b'7668'
 b'5636' b'1276' b'66760' b'544756' b'1332' b'2508' b'76220' b'3824'
 b'83740' b'18468' b'2584' b'2704' b'40360' b'445108' b'5616' b'5388'
 b'7736' b'4816' b'2772' b'9792' b'8960' b'3084' b'149492' b'7224'
 b'10036' b'1360' b'682264' b'530580' b'1232' b'2388' b'16524' b'50876'
 b'78052' b'9416' b'36764' b'16072' b'1404' b'NA' b'21108' b'116796'
 b'4908' b'749048' b'28' b'96324' b'1588' b'998260' b'1620' b'12136'
 b'175948' b'81596' b'6348' b'79408' b'2296' b'62448' b'24836' b'94160'
 b'4564' b'2132' b'3056' b'7744' b'1612' b'11884' b'86400' b'2676'
 b'106456' b'3276' b'10092' b'121208' b'949352' b'9472' b'3096' b'51292'
 b'4268' b'559092' b'7228' b'108' b'5024' b'1560' b'1280' b'24816'
 b'64596' b'2776' b'3124' b'2512' b'4328' b'8808' b'83900' b'5812'
 b'829024' b'3236' b'54436' b'16160' b'5704' b'51304' b'76816' b'2540'
 b'153888' b'64228' b'6156' b'65932' b'4196' b'71188' b'450748' b'9544'
 b'999344' b'2800' b'989708' b'211816' b'7716' b'3092' b'66492' b'1356'
 b'4220' b'2696' b'5084' b'68' b'3532' b'3744' b'49532' b'24584' b'64748'
 b'55532' b'2568' b'20' b'4408' b'46264' b'25108' b'61696' b'15980'
 b'17452' b'809012' b'497400' b'51504' b'1220' b'64088' b'16680' b'68196'
 b'62252' b'3668' b'65260' b'49760' b'2860' b'4160' b'1312' b'949800'
 b'8216' b'3488' b'3392' b'3460' b'28840' b'1324' b'12516' b'11696'
 b'7984' b'11756' b'3772' b'562128' b'3060' b'120872' b'27208' b'3100'
 b'4192' b'8212' b'70544' b'11444' b'56624' b'3144' b'1184' b'348820'
 b'8920' b'17896' b'5080' b'24' b'10412' b'36504' b'110196' b'7108'
 b'15960' b'25124' b'5292' b'813516' b'8388' b'51568' b'12324' b'2572'
 b'1556' b'6784' b'2688' b'19740' b'2108' b'595828' b'1188' b'49676'
 b'15920' b'1464' b'4364' b'65436' b'10792' b'4700' b'92264' b'3808'
 b'51444' b'1248' b'65628' b'2352' b'35548' b'2140' b'3332' b'12540'
 b'58356' b'13520' b'6356' b'66040' b'947664' b'203448' b'65252' b'10896'
 b'949872' b'24000' b'3108' b'16456' b'12176' b'565168' b'3344' b'331880'
 b'45440' b'2440' b'3600' b'360296' b'3700' b'116' b'51752' b'5100'
 b'34608' b'749300' b'32' b'2256' b'64004' b'4104' b'25696' b'8556'
 b'597420' b'17756' b'3268' b'12272' b'2588' b'58892' b'2496' b'14188'
 b'10048' b'193816' b'3720' b'68560' b'71340' b'94812' b'71500' b'18504'
 b'22232' b'9884' b'8560' b'1272' b'25748' b'12544' b'780480' b'104'
 b'583820' b'11848' b'1516' b'48276' b'2460' b'3200' b'184120' b'2848'
 b'1320' b'2244' b'4524' b'41524' b'95160' b'65012' b'344412' b'6968'
 b'3880' b'74704' b'25692' b'10428' b'19172' b'78308' b'55064' b'6212'
 b'1420' b'34716' b'2520' b'4520' b'84160' b'4484' b'5136' b'20236' b'76'
 b'4812' b'14760' b'64136' b'65836' b'32936' b'64096' b'2112' b'11836'
 b'60944' b'10072' b'110704' b'113896' b'14524' b'4172' b'14564' b'3480'
 b'22160' b'56804' b'51864' b'66476' b'3444' b'36836' b'65452' b'22320'
 b'277808' b'36824' b'250336' b'357996' b'777220' b'60928' b'6276' b'1456'
 b'56584' b'119344' b'45708' b'1240' b'788508' b'48600' b'219652' b'7084'
 b'70396' b'7608' b'46036' b'5736' b'23988' b'3736' b'784484' b'9200'
 b'6568' b'11656' b'44412' b'64056' b'64468' b'55000' b'13824' b'7720'
 b'12444' b'42604' b'51372' b'9956' b'7980' b'64828' b'5596' b'8408'
 b'60440' b'58884' b'4292' b'96672' b'51448' b'65948' b'65892' b'12832'
 b'730552' b'52004' b'6132' b'300016' b'56924' b'970360' b'67976' b'16224'
 b'45204' b'66348' b'7896' b'2164' b'1416' b'102292' b'464592' b'761392'
 b'51716' b'785236' b'1528' b'6664' b'52492' b'2348' b'5988' b'757252'
 b'82348' b'1304' b'80216' b'1396' b'7892' b'10892' b'784884' b'1460'
 b'823924' b'8452' b'2868' b'2876' b'86348' b'15808' b'36568' b'5332'
 b'67196' b'4784' b'8956' b'533500' b'63996' b'4964' b'12556' b'16544'
 b'65916' b'76868' b'32960' b'7584' b'25772' b'2148' b'6984' b'7424'
 b'12460' b'55908' b'989584' b'16144' b'10196' b'501784' b'3868' b'4380'
 b'8384' b'946776' b'47016' b'476188' b'908208' b'4704' b'66452' b'5924'
 b'66700' b'65688' b'2552' b'82836' b'582000' b'14608' b'293556' b'125324'
 b'63380' b'7492' b'1328' b'3784' b'99288' b'40584' b'5992' b'6452'
 b'75820' b'955768' b'597460' b'538028' b'3464' b'965648' b'54360' b'5244'
 b'4240' b'8080' b'25684' b'86444' b'947460' b'12656' b'488608' b'64000'
 b'76768' b'66108' b'42636' b'93044' b'30816' b'35028' b'1228' b'87016'
 b'777928' b'12636' b'11160' b'9408' b'4480' b'42484' b'14764' b'5676'
 b'19932' b'8064' b'9140' b'68460' b'56592' b'40396' b'98136' b'2864'
 b'17716' b'66016' b'187560' b'421128' b'108296' b'185700' b'74700'
 b'44404' b'60856' b'2292' b'49552' b'11000' b'1548' b'47592' b'11664'
 b'7704' b'22356' b'76920' b'10208' b'500080' b'13884' b'7436' b'14724'
 b'582564' b'5464' b'172188' b'226108' b'51580' b'144' b'5132' b'2248'
 b'11560' b'5872' b'42392' b'295104' b'3544' b'67244' b'54324' b'56600'
 b'8896' b'65488' b'557344' b'2188' b'9908' b'40' b'31068' b'11592'
 b'147232' b'913992' b'2708' b'10480' b'6612' b'184704' b'10684']
Feature: top_1_60_day_non_fresh_product
Tensor: [b'24980' b'124' b'1352' b'1356' b'2456' b'82084' b'65932' b'956856'
 b'53676' b'10104' b'245488' b'2572' b'2192' b'51504' b'2188' b'3440'
 b'66460' b'88' b'65336' b'8500' b'1284' b'392420' b'2496' b'64616'
 b'835436' b'1312' b'1500' b'54436' b'4116' b'40908' b'1424' b'14796'
 b'1184' b'399060' b'99648' b'2704' b'17756' b'5344' b'1560' b'4196'
 b'65428' b'2492' b'91936' b'7488' b'45244' b'40456' b'77996' b'771148'
 b'1228' b'2412' b'24' b'2584' b'40412' b'813520' b'5080' b'66760' b'8592'
 b'2140' b'60396' b'64088' b'12552' b'2732' b'31068' b'28' b'3488' b'1452'
 b'4408' b'1276' b'25128' b'755440' b'7500' b'66320' b'14828' b'7108'
 b'66376' b'57152' b'20' b'455204' b'9904' b'48688' b'7736' b'64252'
 b'66476' b'8388' b'1232' b'8444' b'74700' b'36328' b'8172' b'6348'
 b'92344' b'7224' b'782860' b'70516' b'274296' b'19740' b'10276' b'602856'
 b'234900' b'116452' b'73268' b'3808' b'1272' b'10756' b'3276' b'76'
 b'10808' b'6844' b'613884' b'326180' b'193816' b'51372' b'9956' b'8252'
 b'65904' b'10792' b'14764' b'11160' b'61112' b'65424' b'9384' b'12176'
 b'173052' b'2132' b'3196' b'51292' b'682264' b'750000' b'4816' b'36504'
 b'1332' b'538028' b'7632' b'454264' b'64280' b'4564' b'2688' b'2256'
 b'2776' b'45568' b'7608' b'3668' b'490528' b'51444' b'82464' b'3200'
 b'70292' b'66252' b'84652' b'2416' b'51448' b'5704' b'488608' b'5240'
 b'66564' b'3476' b'9416' b'87612' b'147824' b'82996' b'502228' b'2556'
 b'10896' b'73244' b'2516' b'14480' b'293556' b'2860' b'64664' b'36568'
 b'955216' b'90296' b'83900' b'25108' b'4016' b'60856' b'908212' b'59608'
 b'746452' b'2460' b'5444' b'3744' b'96600' b'7176' b'14628' b'216276'
 b'65244' b'84372' b'87016' b'4704' b'6612' b'95460' b'68196' b'20000'
 b'5076' b'25132' b'12556' b'24940' b'105900' b'949656' b'750380'
 b'603544' b'48704' b'78672' b'146784' b'65836' b'11732' b'539436' b'1240'
 b'913728' b'25116' b'908208' b'41872' b'77908' b'4160' b'48736' b'300016'
 b'28376' b'581988' b'14524' b'64056' b'48900' b'16696' b'8384' b'68392'
 b'13824' b'2568' b'365544' b'111260' b'89136' b'2452' b'25136' b'52004'
 b'588196' b'2508' b'16116' b'9884' b'3484' b'83740' b'3720' b'501784'
 b'64824' b'76588' b'215712' b'540040' b'2540' b'4192' b'6212' b'91720'
 b'110032' b'11924' b'404856' b'1456' b'1360' b'16456' b'60940' b'233732'
 b'71428' b'11944' b'442208' b'2112' b'6664' b'6156' b'142452' b'66148'
 b'3144' b'7984' b'144768' b'24836' b'598956' b'567196' b'32' b'5688'
 b'959932' b'5616' b'51556' b'12544' b'10036' b'16748' b'66348' b'3028'
 b'12184' b'66796' b'11560' b'17596' b'91696' b'2144' b'3344' b'51716'
 b'597344' b'955168' b'6568' b'11848' b'538184' b'49756' b'62916' b'4700'
 b'1304' b'746308' b'65664' b'78052' b'7492' b'92164' b'966464' b'60444'
 b'12380' b'108' b'67244' b'9544' b'77936' b'18948' b'4948' b'2208'
 b'76396' b'5324' b'85348' b'24816' b'12056' b'10028' b'586936' b'121212'
 b'7712' b'2248' b'574696' b'5404' b'7572' b'982568' b'65696' b'444016'
 b'16' b'761164' b'33276' b'6452' b'2280' b'6364' b'65812' b'56024'
 b'65488' b'583488' b'6072' b'12540' b'9040' b'96944' b'1380' b'2264'
 b'83596' b'64112' b'60904' b'7152' b'3516' b'3828' b'448748' b'782776'
 b'55156' b'75788' b'49448' b'4172' b'331880' b'4560' b'97408' b'183240'
 b'3736' b'65288' b'306644' b'55240' b'98496']
Feature: top_2_60_day_non_fresh_product
Tensor: [b'24984' b'2572' b'65436' b'1352' b'1228' b'2492' b'508720' b'48736'
 b'2188' b'64632' b'2144' b'59624' b'1500' b'5344' b'1312' b'64824'
 b'52004' b'66564' b'70516' b'94472' b'1356' b'557064' b'36488' b'57152'
 b'1424' b'2488' b'88' b'9140' b'909192' b'7712' b'6668' b'12556' b'81596'
 b'65428' b'11200' b'54524' b'455536' b'65140' b'25128' b'10756' b'3668'
 b'66460' b'14796' b'14756' b'8888' b'24836' b'80020' b'4240' b'28'
 b'590676' b'300012' b'65812' b'4564' b'97792' b'63120' b'1560' b'24816'
 b'142952' b'5988' b'65444' b'945984' b'7736' b'60928' b'6664' b'8500'
 b'3056' b'67216' b'124' b'2280' b'5240' b'64596' b'73268' b'530580'
 b'1232' b'9040' b'2688' b'83900' b'2192' b'16800' b'565672' b'3200'
 b'538028' b'1284' b'8444' b'65016' b'5228' b'78180' b'12176' b'1452'
 b'809012' b'2132' b'64616' b'27072' b'2456' b'80024' b'914476' b'67328'
 b'76' b'6612' b'51740' b'118652' b'10092' b'75352' b'949352' b'2352'
 b'24' b'12456' b'82836' b'6364' b'7152' b'51504' b'44480' b'917780'
 b'1276' b'65932' b'762880' b'2520' b'908208' b'2440' b'102400' b'10296'
 b'300016' b'51292' b'8388' b'8104' b'4192' b'11224' b'66476' b'965524'
 b'2556' b'452164' b'10808' b'7668' b'989584' b'73276' b'738512' b'6032'
 b'16676' b'11084' b'10792' b'3144' b'2540' b'32920' b'1324' b'65096'
 b'4572' b'73244' b'16236' b'5688' b'22320' b'83872' b'14628' b'66760'
 b'9416' b'5736' b'45644' b'8592' b'14524' b'603544' b'3460' b'5184'
 b'76404' b'139872' b'2508' b'5080' b'4656' b'10036' b'6356' b'49756'
 b'64088' b'1368' b'4816' b'455204' b'25716' b'6348' b'151936' b'56'
 b'183996' b'91936' b'4948' b'454264' b'2632' b'2460' b'6452' b'65260'
 b'6132' b'67028' b'2584' b'66376' b'41864' b'76200' b'9956' b'2412'
 b'102272' b'61112' b'449588' b'5664' b'5084' b'6352' b'908236' b'36568'
 b'2140' b'12540' b'71500' b'20' b'957420' b'54584' b'1184' b'3196'
 b'4704' b'2304' b'3124' b'16456' b'41872' b'11940' b'3744' b'4408'
 b'68028' b'84372' b'3236' b'65836' b'119632' b'2256' b'51672' b'65708'
 b'31116' b'36312' b'309828' b'12600' b'25108' b'2512' b'160' b'24988'
 b'11632' b'5312' b'10992' b'454504' b'11924' b'91280' b'24000' b'173052'
 b'565772' b'8216' b'785820' b'22160' b'5576' b'41524' b'95160' b'67552'
 b'1512' b'153472' b'5704' b'11560' b'168' b'80536' b'54988' b'71804'
 b'5616' b'64952' b'63380' b'22252' b'84160' b'2676' b'823960' b'11848'
 b'64228' b'555808' b'37684' b'83740' b'34380' b'64280' b'2704' b'49664'
 b'60444' b'100308' b'2516' b'74700' b'10104' b'16600' b'7224' b'108'
 b'1244' b'8252' b'4196' b'957296' b'11708' b'68196' b'45080' b'82604'
 b'966160' b'962964' b'444016' b'561804' b'7492' b'10424' b'12436'
 b'784484' b'7108' b'44412' b'592792' b'80344' b'955756' b'92232'
 b'404856' b'988072' b'3276' b'9376' b'54920' b'17756' b'3736' b'1328'
 b'766544' b'4812' b'66956' b'67976' b'2568' b'2504' b'33276' b'7984'
 b'4328' b'776524' b'36504' b'66332' b'51580' b'4148' b'45796' b'80656'
 b'92344' b'3468' b'989184' b'5636' b'57024' b'12532' b'5508' b'100664'
 b'8960' b'54976' b'89560' b'4688' b'108140' b'9408' b'5444' b'443584'
 b'10896' b'3808' b'970944' b'10892' b'579468' b'6568' b'1248' b'24792'
 b'36824' b'45440' b'964104' b'2296' b'16144' b'6156' b'8384' b'68460'
 b'10428' b'4436' b'49552' b'3324' b'5232' b'80460' b'4668' b'11488'
 b'85456' b'744292' b'51372' b'147572' b'51448' b'5056' b'538596' b'36444'
 b'7880' b'583488' b'5920' b'64096' b'965600' b'59580' b'771140' b'110056'
 b'52672' b'76768' b'18504' b'93044' b'140912' b'71004' b'776584' b'32756'
 b'1212' b'286488' b'25132' b'79380' b'2732' b'41516' b'11160' b'272088'
 b'2180' b'67364' b'42600' b'455356' b'36328' b'28352' b'968940' b'30696'
 b'64664' b'829024' b'40360' b'181092' b'1572' b'8768' b'203036' b'757168'
 b'2860' b'52724' b'12360' b'55172' b'71128' b'87020' b'3428' b'76920'
 b'5104' b'966360' b'25116' b'582564' b'749048' b'32764' b'97980'
 b'606420' b'1548' b'1304' b'737736' b'2288' b'6276' b'683160' b'75256'
 b'9888' b'4956' b'51444' b'65904' b'5672' b'234984' b'68500' b'48664'
 b'362508' b'36528' b'6224' b'4104' b'49452' b'3868' b'41584' b'105704'
 b'77100' b'452160' b'2244']
Feature: top_3_60_day_non_fresh_product
Tensor: [b'8676' b'1284' b'65452' b'119632' b'1356' b'2624' b'968504' b'8180'
 b'2572' b'5844' b'51504' b'64888' b'70312' b'10756' b'609960' b'2412'
 b'1500' b'8500' b'1232' b'7152' b'65444' b'62732' b'7668' b'17756'
 b'2144' b'1244' b'12556' b'2732' b'28360' b'2488' b'1424' b'244148'
 b'1352' b'5464' b'12044' b'11424' b'66564' b'10208' b'1276' b'234900'
 b'2132' b'2192' b'749048' b'2492' b'7108' b'48688' b'3056' b'1228' b'88'
 b'14764' b'124' b'24' b'36528' b'6668' b'108104' b'2280' b'3464' b'70516'
 b'1560' b'31112' b'1184' b'4816' b'41872' b'60944' b'100244' b'2860'
 b'3720' b'66460' b'3880' b'48736' b'1516' b'10092' b'86780' b'2296'
 b'52004' b'10104' b'2352' b'10956' b'966464' b'982392' b'490528' b'51448'
 b'51784' b'404856' b'70784' b'6276' b'87036' b'64596' b'34664' b'11220'
 b'3744' b'6212' b'2188' b'40' b'1452' b'65052' b'956856' b'8756' b'52652'
 b'5872' b'73088' b'36584' b'57152' b'1312' b'60904' b'2456' b'234984'
 b'65096' b'14808' b'6348' b'3200' b'559092' b'51292' b'14588' b'300012'
 b'64636' b'57084' b'10808' b'56160' b'59580' b'19172' b'1240' b'2608'
 b'75152' b'2508' b'42424' b'6156' b'80460' b'44480' b'66108' b'749928'
 b'81684' b'2520' b'62252' b'2332' b'753992' b'37748' b'12136' b'6564'
 b'25108' b'14628' b'3144' b'344412' b'51444' b'51372' b'1220' b'2552'
 b'3092' b'7136' b'160' b'34580' b'67692' b'66476' b'399060' b'71132'
 b'309828' b'2704' b'3484' b'14524' b'24816' b'17452' b'70444' b'12176'
 b'135372' b'4564' b'277808' b'300016' b'1568' b'49712' b'610360' b'5080'
 b'771140' b'49684' b'9040' b'2140' b'112988' b'26352' b'73276' b'258728'
 b'949352' b'60856' b'2256' b'1252' b'12516' b'11944' b'16708' b'4780'
 b'5616' b'7492' b'8408' b'68560' b'9628' b'1344' b'71500' b'7424'
 b'964960' b'3808' b'76808' b'105632' b'67244' b'5228' b'66492' b'191112'
 b'761164' b'4196' b'913772' b'36444' b'3608' b'67216' b'958324' b'8412'
 b'12324' b'1456' b'8768' b'2452' b'84160' b'68304' b'5104' b'15920'
 b'6352' b'5348' b'68276' b'6568' b'45528' b'28' b'7880' b'89688'
 b'682264' b'24912' b'5672' b'12552' b'51752' b'20808' b'2588' b'4408'
 b'181936' b'4704' b'97792' b'906288' b'3596' b'25128' b'84020' b'66568'
 b'90236' b'557064' b'71864' b'331880' b'328828' b'86420' b'447028'
 b'75124' b'5344' b'6132' b'51620' b'227660' b'115876' b'64088' b'596044'
 b'2512' b'597420' b'36852' b'36504' b'199800' b'9504' b'8556' b'11664'
 b'32772' b'33412' b'49760' b'3480' b'3816' b'442416' b'64952' b'48304'
 b'65812' b'780480' b'10896' b'52492' b'33044' b'782860' b'7584' b'16536'
 b'45612' b'4936' b'9956' b'766024' b'11512' b'8064' b'4524' b'10036'
 b'48264' b'74704' b'51660' b'42476' b'11344' b'232832' b'2848' b'51716'
 b'5704' b'6052' b'908244' b'7224' b'1368' b'24940' b'32936' b'20152'
 b'989584' b'11836' b'2388' b'20' b'1740' b'16600' b'3488' b'65428'
 b'22160' b'1756' b'11236' b'57004' b'211980' b'56804' b'8384' b'2208'
 b'3920' b'450356' b'989708' b'91280' b'8388' b'577000' b'2440' b'357996'
 b'77380' b'9544' b'64228' b'3476' b'64280' b'587804' b'557748' b'NA'
 b'957176' b'12096' b'11848' b'55064' b'48412' b'1464' b'3736' b'9408'
 b'967048' b'101384' b'444016' b'912344' b'65968' b'12636' b'3668'
 b'251808' b'12716' b'4112' b'24988' b'682952' b'140004' b'577092' b'5236'
 b'96208' b'501788' b'54464' b'6512' b'776584' b'60396' b'3344' b'785236'
 b'455204' b'83872' b'1404' b'12544' b'908236' b'55256' b'65216' b'71004'
 b'99868' b'7892' b'1304' b'488608' b'25116' b'108' b'47936' b'7736'
 b'770056' b'65696' b'65828' b'5444' b'11432' b'6548' b'91128' b'110196'
 b'36568' b'2416' b'9904' b'908208' b'56996' b'19356' b'786928' b'5944'
 b'117412' b'4572' b'83132' b'597236' b'5136' b'75656' b'502228' b'54976'
 b'16652' b'65892' b'67364' b'17528' b'75256' b'184192' b'66320' b'28344'
 b'19740' b'8592' b'9056' b'754876' b'48608' b'7072' b'65972' b'3784'
 b'583288' b'744460' b'82364' b'175656' b'12436' b'1556' b'5056' b'2516'
 b'3124' b'7984' b'19192' b'52220' b'586936' b'149840' b'59640' b'7572'
 b'125172' b'51556' b'496468' b'79384' b'2776' b'42912' b'24788' b'63196'
 b'8260' b'30816' b'551076' b'81596' b'36848' b'81908' b'9756' b'499452'
 b'7532' b'613884' b'42444' b'903488' b'59332' b'40396' b'770864' b'2268'
 b'70636' b'3096' b'9376' b'8888' b'70292' b'485780' b'80776' b'11024'
 b'1272' b'5240' b'538184' b'4880' b'67976' b'603544' b'64708' b'36824'
 b'12272' b'86436' b'51416' b'200112' b'411544' b'14732' b'6392' b'957816'
 b'4520' b'12360' b'45796' b'14560' b'5004' b'528252' b'51364' b'36396'
 b'766544' b'49764' b'4948' b'51484' b'42612' b'67704' b'32800' b'12656'
 b'78052' b'1736' b'5584' b'26828' b'913992' b'12676' b'6452' b'76'
 b'1324' b'72060']
Feature: top_4_60_day_non_fresh_product
Tensor: [b'88' b'6212' b'1424' b'1500' b'118652' b'124' b'1352' b'174456'
 b'300016' b'51448' b'41872' b'80536' b'66088' b'12552' b'6664' b'2732'
 b'2508' b'2132' b'65336' b'66564' b'62080' b'14760' b'6364' b'17756'
 b'19124' b'45520' b'66108' b'66460' b'3600' b'1284' b'81096' b'300012'
 b'25108' b'949352' b'67704' b'1356' b'2556' b'99648' b'2412' b'12176'
 b'2192' b'4408' b'63120' b'2416' b'34580' b'1452' b'2704' b'57164'
 b'366352' b'173052' b'6380' b'1312' b'61448' b'5312' b'1560' b'1332'
 b'12136' b'173436' b'11512' b'5080' b'78384' b'41864' b'71128' b'2144'
 b'2460' b'60856' b'9676' b'90404' b'5228' b'444016' b'51504' b'84652'
 b'79040' b'91384' b'36824' b'11472' b'293556' b'682264' b'119880'
 b'453788' b'60944' b'49552' b'14628' b'503952' b'64616' b'11236' b'1208'
 b'51412' b'7108' b'4816' b'1472' b'749048' b'65896' b'2304' b'331880'
 b'5240' b'968576' b'65824' b'7152' b'3744' b'3056' b'61696' b'1596'
 b'2492' b'450748' b'51304' b'482208' b'64596' b'5332' b'1276' b'9672'
 b'12344' b'6844' b'530580' b'20' b'3200' b'598592' b'82836' b'2848'
 b'67412' b'9456' b'12260' b'1344' b'908208' b'583488' b'2608' b'10892'
 b'30888' b'66476' b'31116' b'213108' b'16600' b'1304' b'36488' b'5344'
 b'113192' b'1228' b'3276' b'5736' b'10104' b'41780' b'2572' b'51736'
 b'1232' b'9904' b'110032' b'36504' b'108104' b'4564' b'51672' b'56472'
 b'65932' b'7500' b'3464' b'83272' b'3392' b'999344' b'70428' b'7104'
 b'7224' b'10036' b'140036' b'52044' b'611000' b'16272' b'44392' b'76'
 b'5104' b'174788' b'78436' b'91936' b'71440' b'40620' b'6156' b'1456'
 b'987808' b'68236' b'8388' b'67976' b'28' b'1324' b'8500' b'41524'
 b'60840' b'3532' b'3476' b'14732' b'49732' b'56136' b'3808' b'4160'
 b'464592' b'2552' b'3144' b'104968' b'108' b'2568' b'71452' b'65016'
 b'54436' b'6348' b'2180' b'160' b'42424' b'57152' b'10428' b'8216'
 b'6132' b'66320' b'2456' b'196688' b'68572' b'49664' b'61064' b'7492'
 b'8880' b'80068' b'45440' b'3920' b'8556' b'404832' b'5872' b'65444'
 b'375516' b'12656' b'68276' b'7712' b'16800' b'6568' b'83872' b'3564'
 b'3596' b'1184' b'68216' b'64228' b'48664' b'7508' b'36444' b'7560'
 b'10792' b'244148' b'NA' b'761168' b'150100' b'65424' b'10092' b'64088'
 b'811500' b'73244' b'948284' b'95648' b'50708' b'65492' b'780244'
 b'81892' b'57496' b'949792' b'8896' b'66796' b'771296' b'3736' b'4192'
 b'9956' b'454264' b'1432' b'43196' b'35228' b'1420' b'6352' b'4700'
 b'5136' b'76588' b'48412' b'5236' b'4040' b'2208' b'168' b'120' b'22100'
 b'4316' b'44092' b'67364' b'7668' b'9544' b'61112' b'65436' b'2512'
 b'234900' b'27300' b'24' b'80460' b'357704' b'14524' b'5464' b'440168'
 b'11488' b'48276' b'16668' b'60440' b'16544' b'18448' b'64664' b'109364'
 b'467604' b'64136' b'746024' b'908244' b'26404' b'74704' b'21152' b'32'
 b'12556' b'78308' b'66568' b'5688' b'65428' b'92164' b'597840' b'36820'
 b'66448' b'43528' b'44416' b'51484' b'54976' b'11848' b'65216' b'71428'
 b'124800' b'3236' b'3488' b'75124' b'63400' b'9040' b'1748' b'25116'
 b'681956' b'908236' b'3480' b'146784' b'45244' b'164' b'60940' b'12636'
 b'3468' b'36568' b'16696' b'51372' b'16176' b'60928' b'11664' b'52004'
 b'10636' b'14532' b'65816' b'14500' b'904524' b'51716' b'2440' b'84160'
 b'83740' b'50436' b'766024' b'22252' b'950768' b'64824' b'588048'
 b'48704' b'175644' b'1212' b'79408' b'5404' b'736060' b'96216' b'51292'
 b'184636' b'8644' b'78544' b'7884' b'36848' b'16536' b'67508' b'2352'
 b'3904' b'1404' b'26804' b'41040' b'2516' b'4328' b'82996' b'3668'
 b'190232' b'92668' b'489120' b'8720' b'7616' b'99288' b'502584' b'10384'
 b'103364' b'77868' b'16168' b'70516' b'76144' b'152900' b'83900' b'25128'
 b'8064' b'344412' b'8452' b'19740' b'48680' b'9408' b'1464' b'19172'
 b'611596' b'8252' b'2236' b'908212' b'51752' b'514072' b'7080' b'60272'
 b'65812' b'488608' b'75256' b'65916' b'11468' b'24916' b'21300' b'51436'
 b'4380' b'8384' b'68468' b'8540' b'15920' b'51444' b'131140' b'55336'
 b'6204' b'405768' b'1256' b'66452' b'31068' b'5444' b'48624' b'7716'
 b'530380' b'182520' b'33108' b'903488' b'25784' b'66256' b'86140'
 b'771140' b'1320' b'965648' b'10808' b'2860' b'7228' b'141012' b'7980'
 b'86444' b'309828' b'1460' b'6968' b'595828' b'4936' b'24836' b'9376'
 b'22188' b'41496' b'2140' b'430812' b'7876' b'99880' b'756964' b'373576'
 b'4948' b'2248' b'28660' b'565660' b'3124' b'1220' b'9416' b'5508'
 b'809012' b'50876' b'6392' b'2864' b'379780' b'1496' b'97408' b'12620'
 b'64100' b'443368' b'64636' b'2296' b'573728' b'6240' b'1328' b'684088'
 b'11344' b'117400' b'48936' b'1308' b'4520' b'279408' b'914476' b'2264'
 b'66532' b'753992' b'36836' b'24932' b'326180' b'9872' b'1548' b'226108'
 b'64096' b'17392' b'42912' b'2776' b'52220' b'7176' b'5008' b'957504'
 b'10832' b'5476' b'45364' b'56540' b'67688' b'103080' b'79644' b'819108'
 b'533496' b'3720' b'6612' b'4908' b'2532' b'12672' b'150352' b'749112']
Feature: top_5_60_day_non_fresh_product
Tensor: [b'1284' b'12092' b'1500' b'64616' b'31068' b'1424' b'777928' b'757168'
 b'2440' b'51504' b'54988' b'945672' b'65444' b'736296' b'193904' b'5240'
 b'9740' b'1356' b'65932' b'1220' b'47936' b'2624' b'1212' b'124' b'1452'
 b'949352' b'74704' b'3596' b'68204' b'300016' b'565168' b'16456' b'60904'
 b'2492' b'6568' b'1232' b'68276' b'1572' b'565660' b'80460' b'2608'
 b'2264' b'544116' b'64088' b'455204' b'87016' b'83740' b'19740' b'105744'
 b'41872' b'9904' b'17756' b'3428' b'1456' b'88' b'12436' b'37752'
 b'65016' b'2556' b'2256' b'113192' b'1228' b'7224' b'4196' b'34384'
 b'97792' b'8500' b'152556' b'65436' b'66108' b'461164' b'51292' b'1352'
 b'65828' b'5596' b'7152' b'2352' b'65140' b'79160' b'771140' b'64824'
 b'56584' b'8216' b'6348' b'482992' b'2388' b'5812' b'50876' b'70364'
 b'2572' b'98044' b'12032' b'10036' b'125284' b'22252' b'400124' b'566300'
 b'78000' b'2704' b'9344' b'12136' b'82864' b'65496' b'66452' b'3668'
 b'5508' b'6156' b'1620' b'2848' b'66312' b'946780' b'1568' b'443832'
 b'11848' b'92232' b'914476' b'2132' b'2520' b'64704' b'2412' b'7720'
 b'70624' b'6448' b'908236' b'3488' b'1312' b'956972' b'84720' b'44796'
 b'80344' b'5624' b'2512' b'2516' b'54984' b'49664' b'5576' b'16160'
 b'5444' b'374376' b'293556' b'3744' b'2540' b'51348' b'117136' b'76224'
 b'81248' b'2140' b'8672' b'104796' b'9544' b'1276' b'3144' b'12656'
 b'76564' b'184120' b'8464' b'25692' b'10428' b'150304' b'171184' b'55380'
 b'10412' b'765808' b'599032' b'52048' b'2304' b'24584' b'64748' b'908244'
 b'1332' b'24788' b'193816' b'43260' b'8384' b'57152' b'595936' b'4948'
 b'3476' b'14584' b'3464' b'71428' b'50552' b'9320' b'583488' b'6276'
 b'2456' b'767916' b'65248' b'66376' b'117440' b'63016' b'28' b'65836'
 b'60856' b'10908' b'27220' b'7816' b'78876' b'4408' b'3124' b'3920'
 b'16168' b'2192' b'76764' b'44412' b'65420' b'5736' b'2504' b'3408'
 b'48936' b'105900' b'1184' b'11444' b'66332' b'65336' b'5616' b'7220'
 b'2568' b'3604' b'5080' b'12400' b'70516' b'51372' b'24' b'60388' b'3824'
 b'17724' b'6132' b'207580' b'6072' b'581856' b'36348' b'8388' b'2688'
 b'110204' b'12176' b'170588' b'2188' b'32936' b'2392' b'20828' b'784180'
 b'66040' b'1528' b'19928' b'66564' b'4800' b'45612' b'5236' b'NA' b'7492'
 b'103984' b'9956' b'50444' b'81596' b'566344' b'65096' b'7216' b'2148'
 b'116456' b'1244' b'32' b'9676' b'185588' b'4564' b'184704' b'66320'
 b'88408' b'3060' b'9504' b'1328' b'11656' b'3200' b'66460' b'105716'
 b'60444' b'71484' b'51752' b'5664' b'955608' b'55476' b'1404' b'2332'
 b'8556' b'54976' b'85388' b'57116' b'785236' b'4508' b'40920' b'1560'
 b'160' b'10092' b'8552' b'20' b'67976' b'7736' b'244148' b'3720' b'3424'
 b'82996' b'42488' b'36848' b'7572' b'3444' b'1280' b'7668' b'70728'
 b'44692' b'557344' b'33460' b'2732' b'51444' b'7108' b'11560' b'77096'
 b'537452' b'33108' b'64252' b'1368' b'277808' b'60940' b'489216' b'2280'
 b'557064' b'64096' b'6212' b'482220' b'108940' b'9408' b'61064' b'564856'
 b'3460' b'3344' b'24836' b'813516' b'45652' b'51304' b'3808' b'2672'
 b'78124' b'7880' b'65896' b'2108' b'16536' b'7704' b'908208' b'300012'
 b'205884' b'45368' b'56088' b'65816' b'51320' b'84156' b'1200' b'16176'
 b'14524' b'82836' b'84652' b'111260' b'989708' b'76' b'1240' b'11168'
 b'466720' b'21676' b'7716' b'344412' b'3880' b'788508' b'31116' b'52460'
 b'70396' b'36312' b'65524' b'3056' b'737736' b'91280' b'85036' b'115332'
 b'3468' b'84016' b'25128' b'83048' b'4816' b'24940' b'813504' b'558208'
 b'56624' b'84' b'4104' b'10184' b'57620' b'12544' b'247004' b'72'
 b'51448' b'56076' b'452164' b'1552' b'4172' b'7336' b'19512' b'406252'
 b'12204' b'36568' b'45204' b'51584' b'464592' b'108' b'51784' b'71440'
 b'761392' b'7632' b'2508' b'10808' b'76388' b'19172' b'5228' b'12848'
 b'66568' b'3600' b'1188' b'601492' b'42484' b'20880' b'79340' b'965524'
 b'80216' b'19188' b'91936' b'48600' b'113520' b'16224' b'923888'
 b'505332' b'112776' b'88112' b'5332' b'36712' b'614040' b'123432'
 b'16236' b'1272' b'73088' b'55048' b'93620' b'66476' b'682264' b'2696'
 b'11732' b'32960' b'3516' b'65832' b'3828' b'3564' b'56344' b'26068'
 b'11836' b'93044' b'16600' b'30724' b'501784' b'16004' b'2208' b'84976'
 b'214972' b'65488' b'42056' b'2860' b'1464' b'60396' b'66684' b'66348'
 b'94992' b'7168' b'2552' b'501788' b'33276' b'64280' b'4148' b'5388'
 b'102380' b'4328' b'43880' b'43612' b'99288' b'4572' b'4316' b'64136'
 b'6452' b'17448' b'82368' b'2588' b'965604' b'11208' b'9868' b'4380'
 b'12676' b'48264' b'95916' b'56848' b'14732' b'286488' b'598592' b'73408'
 b'51484' b'7888' b'25116' b'66680' b'51864' b'5672' b'113544' b'12260'
 b'430392' b'55620' b'51180' b'2296' b'14764' b'6700' b'66088' b'811132'
 b'5984' b'11156' b'218024' b'102692' b'7084' b'3700' b'592792' b'2524'
 b'2112' b'9804' b'34572' b'82364' b'2728' b'41516' b'67412' b'50872'
 b'1440' b'6816' b'4700' b'766544' b'724144' b'14804' b'414468' b'10104'
 b'1252' b'2144' b'66648' b'273356' b'1304' b'82192' b'186664' b'35688'
 b'1460' b'2176' b'41532' b'51580' b'55064' b'757252' b'48556' b'75788'
 b'6524' b'12056' b'15804' b'7712' b'2260' b'3480' b'59624' b'153888'
 b'3220' b'25108' b'2584' b'196' b'16072' b'36488' b'7616' b'51616'
 b'4524' b'16676' b'40456' b'4160' b'51876' b'6848' b'8920']
Feature: top_1_90_day_non_fresh_product
Tensor: [b'24980' b'124' b'1352' b'1356' b'2456' b'48736' b'2188' b'64632' b'6380'
 b'10104' b'245488' b'2572' b'52004' b'51504' b'7152' b'66460' b'66564'
 b'65336' b'8500' b'1284' b'97792' b'2496' b'64616' b'835436' b'1312'
 b'1500' b'81596' b'65428' b'40908' b'88' b'1424' b'14796' b'1184'
 b'399060' b'99648' b'2704' b'17756' b'5344' b'1560' b'4196' b'2492'
 b'91936' b'7488' b'45244' b'77996' b'771148' b'1228' b'2412' b'24'
 b'40412' b'813520' b'5080' b'10756' b'8592' b'2140' b'60396' b'64088'
 b'14628' b'2732' b'31068' b'28' b'3488' b'1452' b'4408' b'1276' b'25128'
 b'755440' b'7500' b'66320' b'4816' b'14828' b'7108' b'66376' b'57152'
 b'20' b'2192' b'914476' b'48688' b'7736' b'118652' b'8388' b'1232'
 b'8444' b'74700' b'36328' b'8172' b'6348' b'102400' b'16412' b'76224'
 b'70516' b'274296' b'19740' b'51444' b'602856' b'16676' b'73268' b'3808'
 b'10792' b'595936' b'908244' b'3276' b'4812' b'49712' b'67976' b'613884'
 b'326180' b'66760' b'51372' b'3668' b'557064' b'8252' b'65904' b'7224'
 b'603544' b'5184' b'76404' b'14764' b'2508' b'61112' b'65424' b'9384'
 b'12176' b'173052' b'2132' b'3196' b'51292' b'11848' b'750000' b'36504'
 b'1332' b'538028' b'2460' b'2584' b'64280' b'4564' b'2688' b'182520'
 b'2256' b'2776' b'5104' b'45568' b'7608' b'65444' b'490528' b'82464'
 b'44544' b'3200' b'84652' b'956856' b'2416' b'10808' b'51448' b'5704'
 b'488608' b'63996' b'9416' b'87612' b'147824' b'82996' b'65932' b'12552'
 b'502228' b'2556' b'10896' b'73244' b'25108' b'2516' b'14480' b'293556'
 b'2860' b'64664' b'2512' b'955216' b'3480' b'83900' b'4016' b'24912'
 b'908212' b'59608' b'48276' b'5444' b'96600' b'7176' b'908208' b'153472'
 b'84372' b'87016' b'4704' b'6612' b'36568' b'95460' b'68196' b'3744'
 b'737736' b'823960' b'83740' b'12556' b'60856' b'16600' b'949656'
 b'56088' b'25132' b'48704' b'78672' b'65836' b'12540' b'539436' b'966160'
 b'957504' b'41872' b'77908' b'7492' b'10424' b'300016' b'28376' b'581988'
 b'64056' b'48900' b'16696' b'9956' b'8384' b'92232' b'365544' b'89136'
 b'2452' b'5228' b'140004' b'588196' b'16116' b'9884' b'1420' b'3720'
 b'501784' b'64824' b'215712' b'540040' b'1240' b'2540' b'83872' b'6212'
 b'45796' b'110032' b'11924' b'92344' b'11760' b'1360' b'60940' b'233732'
 b'5508' b'71428' b'5332' b'331880' b'442208' b'2112' b'6664' b'6156'
 b'142452' b'66148' b'514072' b'3144' b'7984' b'144768' b'24836' b'537452'
 b'68468' b'16144' b'51556' b'12544' b'51320' b'16748' b'66348' b'3028'
 b'66796' b'24816' b'2144' b'3344' b'51716' b'597344' b'6568' b'81296'
 b'49756' b'62916' b'4700' b'1304' b'746308' b'2520' b'2588' b'78052'
 b'4948' b'92164' b'966464' b'60444' b'4160' b'108' b'17596' b'67244'
 b'9544' b'77936' b'18948' b'76396' b'85348' b'12056' b'65016' b'121212'
 b'3476' b'7712' b'2248' b'574696' b'5404' b'181092' b'65696' b'444016'
 b'16' b'761164' b'33276' b'6452' b'36512' b'2280' b'6364' b'452164'
 b'65488' b'54988' b'454264' b'583488' b'6072' b'97980' b'9040' b'3736'
 b'36444' b'6276' b'83596' b'64112' b'60904' b'12360' b'3516' b'5476'
 b'782776' b'234984' b'75788' b'49448' b'362508' b'20984' b'4560' b'97408'
 b'183240' b'65288' b'306644' b'51868' b'12672' b'55240' b'56460']
Feature: top_2_90_day_non_fresh_product
Tensor: [b'24984' b'2572' b'65436' b'1352' b'1228' b'124' b'508720' b'8180'
 b'65932' b'956856' b'2144' b'6816' b'1500' b'5344' b'1312' b'64824'
 b'2192' b'66564' b'70516' b'94472' b'1356' b'11488' b'88' b'57152'
 b'1424' b'2488' b'2732' b'64888' b'244148' b'51504' b'12556' b'11424'
 b'54436' b'4116' b'11200' b'54524' b'4408' b'10756' b'3668' b'2492'
 b'66460' b'14796' b'14756' b'7108' b'8888' b'24836' b'19420' b'4240'
 b'28' b'66376' b'300012' b'65812' b'1284' b'12136' b'24' b'63120' b'6668'
 b'1184' b'142952' b'78384' b'40456' b'945984' b'7736' b'6664' b'444016'
 b'2860' b'2584' b'67216' b'3880' b'5240' b'64596' b'66760' b'73268'
 b'530580' b'1232' b'9040' b'2688' b'84720' b'503952' b'2352' b'538028'
 b'8444' b'51784' b'404856' b'5228' b'6276' b'12176' b'1452' b'65824'
 b'3744' b'5616' b'2132' b'64616' b'65140' b'65052' b'494860' b'80024'
 b'455204' b'9904' b'73088' b'76716' b'2520' b'6612' b'51740' b'64252'
 b'66476' b'10092' b'908236' b'8500' b'12456' b'82836' b'10808' b'6568'
 b'1276' b'44480' b'917780' b'9408' b'2440' b'25128' b'110032' b'51292'
 b'51672' b'8388' b'37748' b'11224' b'965524' b'2556' b'452164' b'7668'
 b'989584' b'7224' b'64088' b'495964' b'6156' b'116452' b'9812' b'1272'
 b'2704' b'3144' b'70444' b'32920' b'65096' b'10636' b'73244' b'139848'
 b'5688' b'71004' b'83872' b'455536' b'14628' b'193816' b'9416' b'63016'
 b'5056' b'8592' b'9956' b'14524' b'60856' b'10792' b'3460' b'67016'
 b'1560' b'11160' b'4656' b'10036' b'49756' b'49664' b'4816' b'25716'
 b'6348' b'682264' b'300016' b'67244' b'56' b'454264' b'36444' b'6452'
 b'41872' b'67028' b'12204' b'41864' b'2412' b'66040' b'19928' b'6352'
 b'5664' b'12552' b'5084' b'7492' b'36568' b'24912' b'2140' b'3200'
 b'70292' b'66252' b'20' b'16600' b'54584' b'3196' b'4704' b'184704'
 b'2256' b'3124' b'14480' b'68028' b'84372' b'3236' b'908208' b'3476'
 b'35228' b'119632' b'4508' b'65708' b'31116' b'213108' b'309828' b'12600'
 b'67364' b'5736' b'160' b'11632' b'5080' b'65444' b'90296' b'27300'
 b'60192' b'48304' b'565772' b'44692' b'2540' b'31120' b'746452' b'64228'
 b'60440' b'41524' b'95160' b'76364' b'216276' b'65244' b'2516' b'5704'
 b'68572' b'80536' b'48264' b'54988' b'71804' b'2508' b'64952' b'2460'
 b'22252' b'84160' b'5076' b'44416' b'11848' b'555808' b'37684' b'25132'
 b'34380' b'17196' b'24940' b'60444' b'100308' b'6356' b'4564' b'22160'
 b'74700' b'10104' b'25116' b'2208' b'450356' b'1244' b'8172' b'31112'
 b'4196' b'3056' b'146784' b'957448' b'65896' b'1368' b'11708' b'68196'
 b'51716' b'45080' b'82604' b'913728' b'962964' b'4160' b'55064' b'12436'
 b'7608' b'175644' b'80344' b'955756' b'25108' b'3468' b'988072' b'3276'
 b'771140' b'54920' b'83740' b'16536' b'25136' b'100832' b'1404' b'108'
 b'6132' b'2304' b'2568' b'2504' b'17756' b'501788' b'776524' b'36504'
 b'785236' b'66956' b'66332' b'4192' b'4148' b'91720' b'51372' b'98160'
 b'99868' b'8216' b'91936' b'2456' b'12532' b'100664' b'8960' b'54976'
 b'11432' b'60708' b'5444' b'443584' b'67688' b'3808' b'970944' b'8384'
 b'579468' b'3828' b'41032' b'567196' b'5136' b'964104' b'2296' b'501784'
 b'5464' b'51444' b'65836' b'65892' b'4948' b'3324' b'11560' b'66320'
 b'17596' b'1516' b'64280' b'48608' b'4668' b'85456' b'955168' b'51448'
 b'3736' b'7880' b'746316' b'64096' b'65664' b'965600' b'120700' b'59580'
 b'51556' b'32' b'14732' b'52672' b'6212' b'76768' b'12380' b'9376'
 b'32756' b'30816' b'286488' b'5324' b'3596' b'5872' b'586936' b'2180'
 b'52004' b'455356' b'59332' b'50876' b'968940' b'70636' b'64664'
 b'829024' b'40360' b'281424' b'7572' b'1572' b'11024' b'10424' b'12360'
 b'603544' b'3060' b'71128' b'60940' b'76920' b'51320' b'966360' b'582564'
 b'749048' b'51348' b'766544' b'55156' b'1380' b'2264' b'683160' b'4956'
 b'65904' b'83900' b'48664' b'4172' b'67704' b'6224' b'5236' b'3868'
 b'41584' b'12676' b'105704' b'452160' b'14584' b'1324' b'150352' b'98496']
Feature: top_3_90_day_non_fresh_product
Tensor: [b'6348' b'6212' b'65452' b'119632' b'1356' b'2492' b'1352' b'24044'
 b'2572' b'76224' b'41872' b'9396' b'51504' b'70312' b'10756' b'5240'
 b'2412' b'1500' b'65932' b'1232' b'3440' b'65444' b'557064' b'7668'
 b'17756' b'2144' b'949352' b'12556' b'9140' b'66108' b'300012' b'7712'
 b'60904' b'1424' b'25108' b'66564' b'10208' b'1276' b'12176' b'65140'
 b'63120' b'749048' b'2256' b'1284' b'2704' b'57164' b'2488' b'3056'
 b'12436' b'1228' b'590676' b'5312' b'14764' b'8228' b'88' b'4196' b'5080'
 b'97792' b'31112' b'71128' b'1184' b'9676' b'124' b'60928' b'65828'
 b'113404' b'9956' b'66460' b'7152' b'11472' b'8500' b'1516' b'682264'
 b'119880' b'86780' b'7108' b'10428' b'16800' b'5228' b'51660' b'5344'
 b'490528' b'51448' b'28' b'2304' b'78180' b'87036' b'82864' b'4104'
 b'2732' b'2188' b'40' b'81644' b'1452' b'956856' b'482208' b'2192'
 b'52652' b'9672' b'36584' b'76' b'766544' b'234984' b'75352' b'65424'
 b'7224' b'6568' b'51752' b'51292' b'12552' b'84720' b'17916' b'6364'
 b'49664' b'59580' b'2552' b'1240' b'54984' b'6156' b'42424' b'10104'
 b'2520' b'80460' b'44480' b'749928' b'81684' b'1560' b'2456' b'62252'
 b'92344' b'753992' b'7500' b'6452' b'913728' b'9544' b'51444' b'70428'
 b'1220' b'9344' b'10036' b'496084' b'234900' b'2132' b'399060' b'64220'
 b'24812' b'5104' b'174788' b'14524' b'2540' b'9040' b'4564' b'277808'
 b'300016' b'21912' b'771140' b'49684' b'10288' b'60840' b'5736' b'45644'
 b'49732' b'25128' b'73276' b'49760' b'2608' b'60944' b'2568' b'71452'
 b'5616' b'54436' b'16104' b'3144' b'7492' b'4520' b'57152' b'6132'
 b'3200' b'1344' b'83740' b'51648' b'68572' b'90864' b'7424' b'8880'
 b'5444' b'3808' b'76808' b'24' b'151936' b'51372' b'8388' b'183996'
 b'4948' b'41516' b'913772' b'2632' b'68276' b'2556' b'958324' b'12780'
 b'83872' b'2452' b'84160' b'19740' b'4816' b'52004' b'3488' b'102272'
 b'449588' b'45612' b'12324' b'60444' b'7880' b'103980' b'64824' b'5672'
 b'12540' b'71500' b'1528' b'2588' b'4408' b'917948' b'4704' b'9904'
 b'95648' b'32' b'65492' b'16456' b'90236' b'66476' b'328828' b'86420'
 b'771296' b'3736' b'4192' b'34608' b'44984' b'64276' b'5136' b'12532'
 b'5236' b'10828' b'40920' b'11224' b'12136' b'2512' b'24988' b'36568'
 b'65436' b'10992' b'42488' b'91280' b'1404' b'64952' b'65812' b'3824'
 b'41864' b'3744' b'22160' b'7584' b'16544' b'64664' b'537452' b'54044'
 b'1512' b'11512' b'7736' b'8064' b'168' b'91936' b'78308' b'4300'
 b'63380' b'2848' b'2516' b'20000' b'5704' b'6052' b'54976' b'1368'
 b'5688' b'20152' b'124800' b'2352' b'3668' b'2860' b'75124' b'63400'
 b'838576' b'16600' b'65428' b'105900' b'1756' b'11236' b'40476' b'119244'
 b'949832' b'67276' b'2508' b'1200' b'454264' b'48736' b'8252' b'2440'
 b'10636' b'11732' b'14500' b'904524' b'587804' b'NA' b'957176' b'561804'
 b'10808' b'22252' b'64088' b'65524' b'588048' b'44412' b'592792' b'2676'
 b'68392' b'8920' b'36444' b'404856' b'81328' b'66568' b'65968' b'1324'
 b'10896' b'57620' b'12544' b'12716' b'64280' b'452164' b'20' b'2624'
 b'44888' b'577092' b'66956' b'67976' b'3484' b'96208' b'4328' b'76588'
 b'6512' b'776584' b'19172' b'55256' b'65216' b'77868' b'16168' b'112988'
 b'4524' b'51740' b'116388' b'77908' b'488608' b'12580' b'25116' b'47936'
 b'8452' b'770056' b'65696' b'89560' b'11944' b'4688' b'34384' b'9496'
 b'76732' b'108140' b'9408' b'6628' b'908208' b'60940' b'19356' b'786928'
 b'75256' b'60856' b'11468' b'21300' b'83132' b'597236' b'1312' b'24792'
 b'45440' b'603544' b'16676' b'48852' b'16652' b'68460' b'12184' b'1552'
 b'66684' b'2280' b'91696' b'5232' b'8592' b'82836' b'102380' b'65972'
 b'33108' b'82364' b'147572' b'70516' b'15920' b'3124' b'66960' b'19192'
 b'5920' b'965648' b'586936' b'2776' b'149840' b'59640' b'7228' b'7572'
 b'64596' b'110056' b'86444' b'2180' b'24788' b'48952' b'18504' b'93044'
 b'8260' b'1212' b'551076' b'81596' b'81908' b'9756' b'65672' b'914116'
 b'74752' b'613884' b'74704' b'67364' b'42600' b'903488' b'32756' b'36328'
 b'75792' b'2268' b'11432' b'30696' b'12620' b'2728' b'2296' b'982568'
 b'404584' b'36504' b'13776' b'757168' b'52724' b'450340' b'4880' b'32920'
 b'3920' b'87020' b'3428' b'54980' b'411544' b'2416' b'606420' b'1548'
 b'9872' b'57588' b'8616' b'1304' b'957816' b'11560' b'9888' b'7176'
 b'5004' b'528252' b'16512' b'51364' b'2140' b'36396' b'37752' b'68500'
 b'51484' b'2584' b'331880' b'533496' b'12656' b'78052' b'7616' b'1224'
 b'557344' b'26828' b'45620' b'913992' b'400992' b'108']
Feature: top_4_90_day_non_fresh_product
Tensor: [b'88' b'1284' b'1424' b'1500' b'31068' b'2624' b'968504' b'82084'
 b'65444' b'576656' b'51504' b'11684' b'66088' b'12552' b'3596' b'63124'
 b'1312' b'1356' b'8500' b'2132' b'47936' b'65812' b'28' b'62080' b'14760'
 b'1244' b'17756' b'139988' b'909192' b'120828' b'16456' b'7176' b'6568'
 b'300012' b'25128' b'65016' b'2492' b'2412' b'234900' b'455536' b'81596'
 b'2416' b'105744' b'9904' b'66460' b'64664' b'1456' b'124' b'1352'
 b'1560' b'8388' b'66564' b'173436' b'24816' b'9344' b'3124' b'70516'
 b'1276' b'445108' b'31112' b'60856' b'4816' b'41872' b'90404' b'108104'
 b'2352' b'3720' b'79040' b'771140' b'2280' b'48736' b'293556' b'2572'
 b'6204' b'65428' b'12672' b'2296' b'2192' b'64616' b'10104' b'565672'
 b'1208' b'10956' b'400124' b'749048' b'2704' b'70784' b'5240' b'34664'
 b'48756' b'71428' b'5508' b'2452' b'3056' b'4408' b'2848' b'8756' b'2440'
 b'64596' b'160' b'5872' b'67328' b'914476' b'2908' b'2456' b'62996'
 b'264156' b'949352' b'9456' b'12260' b'4692' b'908208' b'2608' b'65932'
 b'30888' b'66476' b'957296' b'57084' b'2144' b'65828' b'4196' b'36488'
 b'89384' b'113192' b'75152' b'7224' b'2348' b'6348' b'79960' b'1232'
 b'4572' b'2520' b'4564' b'2332' b'8104' b'782860' b'6564' b'8444'
 b'83272' b'54524' b'9376' b'999344' b'51372' b'7104' b'1212' b'3144'
 b'3092' b'738512' b'55380' b'611000' b'599536' b'944220' b'57152'
 b'51784' b'2496' b'17452' b'20' b'193816' b'24' b'50876' b'3200' b'22308'
 b'3476' b'7108' b'64088' b'65816' b'911360' b'12556' b'11848' b'3484'
 b'9956' b'55620' b'3744' b'14732' b'14796' b'12176' b'36824' b'5080'
 b'12664' b'78876' b'3488' b'595828' b'9780' b'11944' b'76764' b'584428'
 b'6364' b'68560' b'10428' b'245488' b'6356' b'97080' b'19740' b'7492'
 b'7220' b'60940' b'68512' b'2508' b'51292' b'404832' b'60388' b'5228'
 b'66492' b'191112' b'7632' b'2732' b'908236' b'2568' b'331880' b'67216'
 b'1228' b'7712' b'16800' b'8768' b'3564' b'76200' b'1452' b'68216'
 b'24916' b'1528' b'7508' b'5348' b'7560' b'45528' b'NA' b'34740' b'89688'
 b'44484' b'20808' b'65424' b'957420' b'1184' b'9676' b'70312' b'68572'
 b'84020' b'57496' b'949792' b'4948' b'36388' b'8300' b'75124' b'60444'
 b'5344' b'601112' b'227660' b'99992' b'2256' b'70476' b'2512' b'65836'
 b'6352' b'4700' b'551012' b'36852' b'36504' b'16600' b'9504' b'65096'
 b'120' b'51580' b'44092' b'7668' b'36444' b'32772' b'244148' b'61112'
 b'33412' b'300016' b'48704' b'11924' b'1220' b'24000' b'2516' b'3668'
 b'8216' b'10896' b'52492' b'440168' b'11488' b'785820' b'33044' b'5576'
 b'51716' b'16536' b'18448' b'4524' b'16676' b'64136' b'86924' b'67552'
 b'2148' b'277808' b'205884' b'88716' b'11560' b'65672' b'10036' b'66568'
 b'44480' b'11344' b'92164' b'65148' b'36820' b'908212' b'55064' b'908244'
 b'51484' b'65216' b'32936' b'2488' b'922404' b'3236' b'541232' b'9040'
 b'1740' b'5236' b'10808' b'81512' b'1332' b'3480' b'71080' b'45244'
 b'56804' b'64340' b'8556' b'592792' b'82108' b'12636' b'989708' b'51444'
 b'14524' b'14480' b'577000' b'357996' b'66348' b'60928' b'11768' b'64228'
 b'21676' b'6132' b'5704' b'6212' b'557748' b'50436' b'766024' b'538028'
 b'48412' b'1464' b'3736' b'784484' b'967048' b'36568' b'1240' b'444016'
 b'79408' b'7936' b'912344' b'111260' b'813504' b'122128' b'251808'
 b'247004' b'7884' b'4112' b'36848' b'1328' b'25108' b'8252' b'78308'
 b'96684' b'22848' b'4812' b'41040' b'7984' b'82996' b'87016' b'190232'
 b'92668' b'3344' b'455204' b'8720' b'7616' b'71440' b'12544' b'67704'
 b'71004' b'404856' b'53648' b'816152' b'579468' b'57024' b'61588' b'6156'
 b'2688' b'6548' b'611596' b'110196' b'45572' b'51752' b'179880' b'64096'
 b'93620' b'488608' b'5944' b'10892' b'11732' b'32960' b'3516' b'117412'
 b'5688' b'40456' b'598956' b'11772' b'502228' b'959932' b'54976'
 b'214972' b'5476' b'104968' b'49552' b'405768' b'4104' b'7168' b'501788'
 b'5444' b'113056' b'5388' b'80460' b'214408' b'530380' b'4328' b'43684'
 b'583288' b'175656' b'67244' b'12436' b'1556' b'25784' b'42424' b'48268'
 b'52220' b'7584' b'544116' b'2860' b'12676' b'11044' b'6612' b'14764'
 b'65436' b'82852' b'2776' b'1460' b'4364' b'63380' b'4464' b'76' b'2140'
 b'7876' b'87424' b'65904' b'272088' b'561920' b'15920' b'80780' b'753992'
 b'603544' b'2584' b'11156' b'83900' b'770864' b'76132' b'543076'
 b'379780' b'3096' b'97408' b'51556' b'4248' b'64100' b'34572' b'64636'
 b'70292' b'41516' b'5104' b'80776' b'121356' b'770056' b'3880' b'1272'
 b'538184' b'766544' b'50848' b'3460' b'12656' b'86436' b'54316' b'76252'
 b'200112' b'279408' b'83872' b'2264' b'66532' b'32764' b'36836' b'2152'
 b'24912' b'326180' b'35688' b'2288' b'75928' b'7888' b'74812' b'75256'
 b'45796' b'14560' b'5008' b'957504' b'448748' b'78384' b'2436' b'45364'
 b'56540' b'67688' b'737736' b'36528' b'11468' b'1344' b'54988' b'56'
 b'49452' b'586028' b'76220' b'16696' b'61428' b'2244']
Feature: top_5_90_day_non_fresh_product
Tensor: [b'2192' b'12092' b'1500' b'2572' b'118652' b'1424' b'777928' b'922968'
 b'51580' b'3596' b'54988' b'13860' b'25128' b'736552' b'6664' b'12656'
 b'88' b'1220' b'65336' b'2624' b'62732' b'4408' b'1452' b'949352' b'6364'
 b'85648' b'2872' b'300016' b'66460' b'3600' b'1284' b'2492' b'4192'
 b'1232' b'65428' b'1560' b'541712' b'80460' b'2608' b'99648' b'54980'
 b'64088' b'455204' b'87016' b'66564' b'34580' b'14760' b'5672' b'75124'
 b'12324' b'173052' b'3344' b'1276' b'1356' b'2552' b'16160' b'817352'
 b'113192' b'97792' b'36528' b'4112' b'1352' b'45612' b'5988' b'41864'
 b'73540' b'2144' b'12640' b'51292' b'11220' b'10756' b'17680' b'464592'
 b'9792' b'7152' b'84652' b'21676' b'1228' b'3488' b'56584' b'2352'
 b'2556' b'6348' b'6212' b'2388' b'16524' b'49552' b'19740' b'9416'
 b'51504' b'98044' b'1184' b'12032' b'3200' b'982392' b'2132' b'1472'
 b'2540' b'10104' b'331880' b'6548' b'124696' b'3744' b'6156' b'3828'
 b'1620' b'4284' b'1596' b'450748' b'51304' b'124' b'59868' b'11848'
 b'92232' b'12344' b'65696' b'3120' b'60904' b'598592' b'66348' b'2848'
 b'65096' b'14808' b'12436' b'6448' b'559092' b'10892' b'450624' b'64636'
 b'64952' b'16600' b'56160' b'44796' b'5344' b'108' b'3476' b'1312'
 b'16456' b'2732' b'1368' b'9676' b'5444' b'10296' b'36504' b'293556'
 b'9504' b'8556' b'14628' b'67688' b'10808' b'4656' b'7136' b'5652'
 b'64664' b'10412' b'16272' b'44392' b'5576' b'10036' b'51448' b'7224'
 b'24584' b'78436' b'91936' b'24788' b'9408' b'1324' b'4816' b'4948'
 b'565168' b'4572' b'16236' b'94352' b'12136' b'2508' b'6844' b'169888'
 b'205884' b'41524' b'66376' b'65524' b'51660' b'66760' b'65260' b'186656'
 b'906284' b'538028' b'3144' b'6220' b'3920' b'24' b'12516' b'31112'
 b'16708' b'11444' b'4196' b'41872' b'65420' b'2504' b'31068' b'8216'
 b'12848' b'66320' b'196688' b'61064' b'28' b'964960' b'45440' b'3532'
 b'65444' b'99956' b'5688' b'5704' b'957448' b'375516' b'43976' b'207580'
 b'48408' b'908212' b'3608' b'3124' b'16268' b'45600' b'12176' b'2392'
 b'2568' b'68304' b'84372' b'8384' b'45572' b'15920' b'8500' b'2704'
 b'65436' b'8388' b'10792' b'6032' b'7876' b'NA' b'4520' b'761168'
 b'34748' b'50444' b'81596' b'37576' b'42912' b'10092' b'6568' b'32'
 b'73244' b'51444' b'948284' b'11224' b'4708' b'50708' b'604164' b'66568'
 b'1328' b'11940' b'11656' b'2440' b'28864' b'105716' b'600900' b'9956'
 b'454264' b'7980' b'43196' b'35224' b'76776' b'5184' b'597420' b'54976'
 b'76588' b'944116' b'199800' b'79608' b'22100' b'32936' b'357996'
 b'945672' b'9544' b'3424' b'234900' b'454504' b'1380' b'2412' b'53668'
 b'36312' b'45568' b'1304' b'203404' b'84852' b'3464' b'81016' b'6612'
 b'7108' b'11560' b'2248' b'33108' b'64252' b'20' b'5228' b'603828'
 b'7492' b'74704' b'60444' b'66332' b'2280' b'67644' b'66476' b'809012'
 b'64096' b'42476' b'108940' b'597840' b'2408' b'14560' b'3460' b'2676'
 b'5136' b'1332' b'14500' b'3056' b'65836' b'24940' b'17772' b'989584'
 b'97408' b'78124' b'7880' b'3808' b'16536' b'551012' b'1748' b'300012'
 b'7572' b'908236' b'1572' b'2688' b'174788' b'211980' b'94160' b'65816'
 b'7712' b'3444' b'36568' b'1496' b'16176' b'66088' b'77380' b'11168'
 b'11664' b'89980' b'957296' b'344412' b'48600' b'3880' b'586936' b'57152'
 b'244148' b'24356' b'2180' b'749048' b'54348' b'101384' b'452160'
 b'115332' b'13824' b'10108' b'75584' b'16544' b'5404' b'3060' b'51372'
 b'83048' b'99472' b'96216' b'36848' b'1488' b'9376' b'3384' b'506276'
 b'55620' b'61112' b'908208' b'8768' b'25116' b'4172' b'682952' b'766544'
 b'47852' b'60944' b'49664' b'488608' b'5236' b'51584' b'4328' b'33276'
 b'91720' b'56804' b'71440' b'2348' b'60396' b'7176' b'681956' b'9040'
 b'502584' b'65664' b'169984' b'9768' b'1456' b'989184' b'51752' b'113520'
 b'68276' b'68252' b'36712' b'19172' b'8252' b'14580' b'40360' b'82836'
 b'140256' b'66108' b'682264' b'4564' b'65916' b'12676' b'24916' b'3276'
 b'4380' b'2860' b'11472' b'1248' b'338572' b'36444' b'160' b'592792'
 b'48968' b'40456' b'2208' b'84976' b'1212' b'131140' b'273356' b'6204'
 b'4704' b'48556' b'184192' b'60452' b'55048' b'65812' b'10428' b'582000'
 b'1464' b'9056' b'754876' b'48624' b'7072' b'182520' b'207192' b'744292'
 b'903488' b'82996' b'3284' b'64136' b'66256' b'42444' b'86140' b'452164'
 b'8592' b'14764' b'48264' b'14584' b'6132' b'496468' b'968840' b'231860'
 b'6968' b'84160' b'595828' b'73248' b'9344' b'51484' b'776584' b'5388'
 b'60856' b'44412' b'65496' b'78408' b'113544' b'99880' b'2488' b'499452'
 b'430392' b'51180' b'28660' b'118800' b'5080' b'56592' b'181912' b'168'
 b'218024' b'3700' b'2524' b'3212' b'82364' b'100032' b'12056' b'485780'
 b'94792' b'3736' b'65620' b'48852' b'64100' b'103952' b'4700' b'2140'
 b'724144' b'67976' b'65140' b'14524' b'64824' b'7532' b'404856' b'16652'
 b'82192' b'82248' b'2420' b'24932' b'65932' b'5096' b'20904' b'6392'
 b'1548' b'537168' b'108812' b'17392' b'2776' b'8448' b'24836' b'1256'
 b'966160' b'16696' b'59624' b'16624' b'49764' b'2188' b'5084' b'32800'
 b'16072' b'36488' b'80424' b'3824' b'4524' b'76232' b'544076']
Feature: Total_spend
Tensor: [6.3630461e+04 1.7847666e+04 8.0024941e+03 6.4460698e+03 1.7453709e+04
 4.4308350e+03 8.5073848e+03 5.4749465e+04 6.0934678e+03 2.6506469e+05
 5.5260361e+03 5.0634831e+05 2.9048040e+03 4.8849832e+04 3.9899341e+03
 2.4073496e+04 4.1265925e+05 6.9135029e+03 7.3950122e+03 2.0685727e+04
 1.9158292e+05 9.9065342e+03 6.1226729e+03 4.2850259e+03 1.2993336e+05
 3.5136179e+03 4.1555161e+03 7.0525367e+04 6.2798328e+04 2.1122303e+05
 6.4703608e+03 9.9786416e+03 1.0580913e+05 3.6447086e+04 1.0918341e+04
 4.9065840e+03 1.0415799e+04 2.9817361e+03 3.3996421e+03 1.5835410e+03
 4.4613091e+03 7.0310161e+03 1.1209932e+04 3.9660102e+04 1.5659806e+05
 2.1961225e+04 1.6722324e+04 1.0948554e+04 4.1280122e+03 7.7083921e+03
 4.8530078e+04 8.0993882e+03 3.0368879e+03 4.1956021e+03 1.2900231e+04
 3.1426523e+04 4.8013945e+04 3.8410740e+03 3.4923149e+03 1.0119710e+05
 1.8235871e+04 1.4785452e+04 5.7138301e+03 4.5418408e+03 1.8478260e+03
 1.7515484e+04 2.8042200e+03 5.9766748e+03 2.3800969e+04 4.7289150e+03
 2.8409148e+04 2.1378240e+03 7.3997102e+04 4.9700512e+04 1.4057811e+04
 1.5703983e+04 2.6644409e+03 8.1605342e+03 1.3649616e+04 2.9378654e+04
 2.2111741e+03 1.6654590e+03 2.6117496e+04 2.2319370e+03 4.4717219e+04
 1.3335660e+04 7.2050488e+03 2.1243168e+04 1.6617870e+03 2.4314939e+03
 1.4315310e+03 1.3983948e+04 1.2577806e+04 1.0160154e+04 2.5487371e+03
 7.1774731e+03 1.0491669e+04 1.6287489e+04 1.1454849e+04 1.3574151e+04
 6.9803461e+04 7.7896260e+03 1.7157061e+03 2.2284541e+03 3.2972849e+03
 7.5039945e+04 6.5606401e+03 1.6998120e+03 4.9700249e+03 1.3400452e+05
 5.9882490e+03 1.4794749e+04 3.2037571e+03 2.0560607e+04 8.0513098e+02
 1.1891664e+04 2.3322617e+04 4.0373369e+03 1.6833365e+04 2.5560062e+04
 2.8665271e+03 2.5257023e+04 2.5618860e+03 4.7966221e+03 2.3469867e+04
 3.9382191e+04 2.1625623e+04 5.0223149e+03 6.3071909e+03 1.4730840e+03
 3.9326840e+04 1.1366408e+05 1.7988210e+03 9.6193623e+03 3.7484027e+04
 8.4446553e+03 1.7439436e+04 2.3370229e+04 1.6928234e+04 3.1676373e+04
 3.0247199e+04 4.3958970e+03 1.3936770e+03 2.2222387e+04 3.0671027e+04
 2.9696040e+03 1.2683889e+04 7.5344580e+03 1.2277575e+04 3.2255459e+03
 1.0179900e+03 1.6453395e+04 1.5992181e+04 1.7855244e+04 9.7990830e+03
 5.5740601e+03 1.4874921e+04 1.3768902e+04 1.6253280e+04 1.9738890e+03
 2.3301621e+04 2.3449771e+03 7.9380000e+03 9.9279717e+03 2.5734331e+03
 1.2126756e+05 1.4799780e+03 3.2805630e+03 1.5987492e+04 3.9867930e+03
 1.9269549e+04 2.3541066e+04 2.1637232e+04 2.4963578e+04 8.5394248e+03
 1.9127098e+04 9.6441660e+03 1.2963330e+03 2.7537661e+03 1.7869680e+03
 2.5480629e+04 5.4137070e+03 1.0540107e+04 1.4564160e+03 2.3307346e+04
 1.1812321e+03 6.9923000e+04 9.5675400e+03 2.1890225e+05 1.4745330e+03
 2.7027773e+04 1.0781550e+04 1.9208610e+03 1.7224740e+03 3.6135000e+03
 5.0946238e+04 1.1503134e+04 2.0601324e+04 2.1955320e+03 1.6267140e+04
 5.4060122e+03 3.5473140e+03 2.2800239e+03 2.6021205e+04 2.0494160e+04
 8.9901445e+03 5.3138789e+03 1.2095901e+05 7.6217129e+03 2.7472445e+04
 1.5722208e+04 1.8166859e+04 5.5486260e+03 1.3322045e+05 1.5044670e+03
 2.0736521e+04 6.1443901e+03 2.0135709e+04 1.0527075e+04 3.3466951e+03
 3.0901230e+03 1.5914611e+03 3.1364369e+04 2.1398850e+04 2.0927727e+04
 3.9317246e+04 4.0517801e+04 4.0344148e+04 9.3457354e+03 5.5300322e+03
 1.3312800e+03 1.6288821e+04 1.8186967e+04 1.4124978e+04 1.9823652e+04
 1.4268060e+03 3.4942410e+03 3.4190953e+04 3.2438008e+04 2.3996133e+04
 2.7008101e+03 2.1387959e+03 2.5440930e+03 1.0894950e+03 1.2862764e+04
 4.2295699e+04 1.6813305e+04 1.1815857e+04 1.2211812e+04 5.7083218e+03
 6.4922129e+03 4.4768359e+04 5.2830088e+03 1.7743248e+04 3.6460891e+03
 3.5391150e+03 3.8823301e+03 1.2690783e+04 3.5549109e+04 2.5785404e+04
 1.5673806e+04 2.1799891e+04 2.2000645e+04 1.2210516e+04 1.7239635e+04
 1.8079371e+04 1.2288555e+04 6.9002100e+02 2.0930129e+03 8.5602783e+03
 1.5107508e+04 6.5447965e+04 2.4787710e+03 2.0899980e+03 1.1025179e+03
 8.2720439e+03 4.4599951e+03 2.1554460e+03 4.5672388e+03 3.7963081e+03
 3.8340811e+03 1.1995902e+04 2.2953960e+03 4.7232297e+04 3.3095339e+03
 1.1048517e+04 3.9547351e+03 2.4117930e+03 4.4293742e+04 6.9147469e+04
 1.6935740e+04 2.3458303e+04 1.2322440e+03 2.0087117e+04 5.2606440e+03
 1.5325803e+04 1.8669420e+03 5.3130059e+03 6.4220132e+03 2.5785901e+03
 7.8225210e+03 1.3904595e+04 6.8783398e+02 3.3000300e+03 3.3332310e+03
 4.0760371e+03 3.0056688e+04 2.7268857e+04 4.0367429e+03 2.7417329e+03
 9.5470918e+03 3.3004351e+03 3.5625239e+03 2.8374299e+03 3.5057520e+03
 1.0177929e+04 1.8500635e+04 1.4487300e+03 3.4329600e+03 1.3342518e+04
 2.7136980e+03 4.4535869e+03 1.6344720e+03 3.8091689e+03 4.0800420e+03
 1.0760526e+04 1.3185189e+04 5.6998530e+03 2.2979475e+04 1.9799055e+04
 1.4203530e+03 2.6132581e+03 6.7487310e+03 1.4089068e+04 1.9273950e+03
 1.1536740e+03 1.0479060e+04 7.4049453e+04 1.9926441e+04 8.0525698e+03
 2.8364670e+03 7.3469702e+02 7.6553730e+03 2.2617900e+03 4.4650855e+04
 1.2889008e+04 2.8927800e+03 1.5765210e+03 1.5707907e+04 5.7670469e+03
 5.8961188e+04 1.0849950e+03 2.1077199e+04 8.3107803e+03 1.1358450e+04
 6.6244678e+03 2.7672300e+03 1.3491810e+04 7.8442920e+03 7.9813711e+03
 7.7972671e+03 1.0185327e+04 1.0000152e+04 9.1955156e+03 3.7176389e+03
 1.2437010e+03 1.4885820e+03 4.7274516e+04 1.8914940e+03 3.1994424e+04
 1.3032918e+04 3.5601867e+04 6.5477158e+03 1.4367330e+03 5.0291548e+03
 8.8126924e+03 1.3473216e+04 2.7490410e+03 1.3805551e+03 2.0974994e+04
 2.0205990e+03 8.8212871e+03 5.8471650e+03 1.7150850e+03 1.2267846e+04
 2.2892400e+03 9.1740596e+03 9.6827399e+02 1.4749191e+04 6.6424500e+02
 1.9198494e+04 3.8036195e+04 1.5859800e+03 2.1551399e+03 8.3142266e+03
 1.8012320e+04 2.4913539e+04 2.8046971e+04 4.1707979e+03 1.8374760e+03
 8.8223401e+02 1.4307480e+03 3.4782390e+03 3.1124492e+04 1.1367054e+04
 7.6568940e+03 1.1650905e+04 2.2058010e+03 1.1388150e+04 1.4095350e+03
 3.8484990e+03 2.7018035e+04 8.9519941e+03 6.1488091e+03 6.3395552e+03
 2.4441750e+03 2.6114761e+03 1.0627290e+03 8.4496504e+03 1.7210970e+03
 1.4891688e+04 8.1810718e+03 3.7128781e+04 9.1562852e+03 2.5017930e+03
 2.2382549e+03 4.0922371e+03 1.4157846e+04 1.3602419e+03 1.6727887e+04
 1.3930803e+04 4.0319280e+03 5.6990996e+04 3.2816790e+03 2.3248711e+03
 3.6566785e+04 1.3727430e+03 4.8200220e+03 5.3907300e+03 3.1743359e+03
 8.5340068e+03 4.0669919e+03 1.0171296e+04 6.7312529e+03 1.1475081e+04
 7.9457041e+03 1.6779150e+03 9.2818799e+03 1.3978710e+03 9.1928477e+04
 1.3727340e+04 2.6900640e+03 1.0123884e+04 5.2683208e+03 2.1822930e+04
 1.9892789e+04 2.2559912e+04 1.0062540e+04 3.9573820e+04 8.0108133e+04
 6.3766803e+02 8.5423496e+03 6.9073110e+03 3.8697184e+04 6.8405402e+02
 2.0642697e+04 8.0755539e+04 2.8953793e+04 1.6248357e+04 4.6641152e+03
 2.6585758e+04 8.9499424e+03 1.1655747e+04 2.8129465e+04 1.7048430e+03
 3.0267307e+04 4.1731289e+03 1.9370709e+04 5.2424639e+03 9.6408899e+02
 3.8525581e+03 1.8399951e+04 3.9192749e+03 1.2318571e+03 3.2103369e+04
 2.5864470e+03 2.1794670e+03 1.4180589e+04 1.8565470e+03 1.0943370e+03
 1.7026748e+04 1.1786229e+04 1.2740112e+04 2.9085659e+03 8.6764250e+04
 9.1740508e+03 3.4333020e+03 6.8499180e+04 6.0856831e+03 2.6509861e+03
 9.0038702e+02 8.6999404e+03 5.4486182e+03 1.9715570e+04 2.3016599e+03
 1.1763225e+04 1.8268290e+03 6.1175518e+03 1.4068476e+04 9.8425800e+02
 2.8635012e+04 1.3572054e+04 1.3986027e+04 1.0759707e+04 5.8332241e+03
 1.7768178e+04 1.9501740e+03 1.9851660e+03 7.2273602e+02 4.1108491e+03
 1.2163592e+05 8.1818462e+03 2.8470959e+03 2.6429293e+04 5.2010371e+03
 1.6844580e+03 1.8064457e+04 3.1788540e+03 7.7898508e+04 1.3749831e+04
 8.1744299e+02 2.2321908e+04 1.1569950e+03 1.3033116e+04 3.7556633e+04
 1.0456704e+04 2.0602981e+03 1.6987679e+03 5.7158099e+02 1.7424324e+04
 1.0710000e+04 3.5852490e+03 1.3980690e+03 1.1830320e+03 8.2129590e+03
 1.1704563e+04 2.8341809e+03 1.5680430e+03 1.0477350e+03 1.3290389e+03
 4.3983809e+03 2.6031509e+03 9.2517568e+03 8.0326982e+03 2.2275379e+04
 1.0133370e+03 2.3861431e+03 7.3140571e+03 2.1036889e+04 8.2017178e+03
 7.9247520e+03 1.5720570e+03 1.8526941e+04 1.2207780e+04 1.1066454e+04
 4.5255962e+03 2.2020939e+04 1.1499750e+03 5.7737701e+02 3.7758601e+03
 7.5925620e+03 3.1223537e+04 8.3903223e+03 1.6569540e+03 7.4589302e+03
 1.3873482e+04 2.8453689e+04 4.5752939e+03 2.4961321e+03 8.8400702e+02
 2.7262529e+03 1.0567467e+04 8.4709707e+03 1.4085090e+04 1.0682469e+04
 2.7012348e+04 2.7933760e+04 1.0934523e+04 3.9751021e+03 6.3787051e+03
 1.4683051e+03 1.1756250e+03 9.7632900e+03 5.7246572e+03 1.0141470e+03
 3.5875620e+03 6.3489600e+02 9.3705303e+03 8.2735557e+03 1.1020626e+04
 9.8261553e+03 2.1880566e+04 9.5356797e+03 3.7840680e+04 1.0750590e+03
 1.4838714e+04 5.8719780e+03 2.3659919e+03 1.4252193e+04 1.5931026e+04
 1.8214290e+03 5.1469380e+03 9.9329043e+03 1.4487318e+04 6.6422881e+03
 1.7688662e+04 7.4994658e+03 2.1630779e+03 4.9674238e+03 1.3836870e+04
 4.0290659e+03 2.4665301e+04 3.4809121e+03 7.2074203e+04 1.4767469e+03
 5.8919312e+03 2.7209160e+03 1.4674771e+03 1.9156373e+04 1.2960540e+03
 6.3811348e+03 6.1250581e+03 2.8350604e+04 5.9513491e+03 3.1909320e+04
 1.7042635e+04 1.4978700e+03 3.4237800e+03 9.8669971e+03 4.5715500e+02
 4.1849129e+04 7.8953400e+02 5.3557202e+03 1.6239960e+03 2.7364680e+04
 1.3346784e+04 3.2392080e+03 1.7402273e+04 1.1470293e+04 1.2419082e+04
 1.3559580e+03 1.8111303e+04 5.0786279e+03 1.1353095e+04 2.5572061e+03
 9.9911700e+02 7.9864019e+03 6.1554692e+03 1.2631770e+03 7.1719741e+03
 6.0523199e+02 1.2753423e+04 7.3199429e+03 6.4975500e+02 2.8539027e+04
 1.4032782e+04 2.3418269e+03 5.2116572e+03 5.2908102e+04 8.7907139e+03
 1.5006330e+04 1.0518345e+04 1.0049535e+04 2.2139189e+03 1.3834782e+04
 1.4500755e+04 7.5824639e+03 1.5715980e+03 1.5117876e+04 7.6104360e+03
 4.7776768e+03 1.0369107e+04 8.5090498e+03 7.1018281e+03 1.4376870e+04
 5.4971997e+02 3.9127319e+03 3.5431379e+03 3.0905289e+04 2.8732859e+03
 1.0871595e+04 1.9349370e+03 5.8351230e+03 1.5971940e+03 5.6804580e+03
 1.8003455e+04 3.0913110e+03 1.4354235e+04 5.3502568e+03 1.5234588e+04
 2.2281841e+03 2.1430979e+03 1.0890900e+04 1.2596085e+04 2.7638911e+03
 7.4412002e+03 1.4446620e+03 3.1793553e+04 1.2489327e+04 1.3467195e+04
 2.4062086e+04 2.5323931e+03 9.5085898e+03 7.6746600e+02 1.9352547e+04
 1.6129440e+04 1.2458070e+04 1.1607372e+04 8.5207501e+02 3.1198672e+04
 1.5832531e+03 1.3994181e+04 7.2290610e+03 5.0491709e+03 3.1940289e+04
 5.7108779e+03 4.5688113e+04 2.2196609e+03 7.3796938e+03 1.9919629e+04
 8.8967969e+03 1.8404793e+04 5.2150500e+02 1.6216362e+04 1.7316899e+03
 1.8111689e+04 1.8870975e+04 8.8932598e+03 7.7209111e+03 6.5889422e+04
 1.2393837e+04 3.6274141e+03 3.0771089e+03 4.5262979e+03 1.3061412e+04
 4.7715479e+03 1.1242377e+04 2.2201741e+03 1.0417482e+04 1.3738806e+04
 1.1782305e+04 3.5837129e+04 3.1626721e+03 8.1114028e+03 1.0895445e+04
 2.1441016e+04 1.0462321e+03 7.3851841e+03 5.3036548e+03 1.1984940e+03
 5.5480322e+03 4.2675391e+03 5.0371558e+03 1.0728090e+03 4.6737406e+04
 1.9600316e+04 2.0311434e+04 9.3978900e+02 2.7626805e+04 1.3971150e+03
 6.2990100e+02 2.1517739e+03 1.6855037e+04 3.2178330e+03 4.0012930e+04
 2.3075820e+04 7.3813770e+03 6.3981992e+03 9.2103838e+03 2.8914939e+04
 1.5640291e+03 5.0034512e+03 2.2611060e+03 4.0452949e+04 8.9180820e+03
 7.1424810e+03 6.1789590e+03 2.7846766e+04 7.5700708e+03 1.9832400e+03
 4.1757842e+03 1.6471980e+03 6.8740198e+02 4.2002642e+03 7.9335088e+03
 7.5028950e+03 2.0228266e+04 2.1353401e+03 4.8995459e+03 3.5004780e+03
 1.5580350e+03 7.1652871e+03 1.0692629e+03 1.1958021e+04 1.7308395e+04
 9.8236260e+03 2.7135090e+04 4.0979248e+03 1.6126740e+03 5.3455322e+03
 2.1081438e+04 3.3031746e+04 1.4246550e+04 8.5146594e+04 2.9661299e+03
 1.0687590e+03 2.6223479e+03 1.6763867e+04 1.3446000e+03 1.0795050e+03
 2.0143467e+04 4.6139668e+03 1.6926453e+04 5.9747310e+03 1.4429124e+04
 8.6232422e+03 6.1546547e+04 4.7795308e+03 5.4226982e+03 2.9389319e+03
 1.5881580e+03 4.8300316e+04 4.3887871e+03 8.2188994e+03 6.4676519e+03
 6.2046812e+03 5.9636250e+03 5.2711470e+03 1.3175829e+04 5.9563530e+03
 9.3983936e+03 5.8173032e+03 3.4227262e+04 2.1697290e+03 8.1049500e+02
 1.4942718e+04 1.3107330e+03 8.2610999e+02 7.8549751e+03 3.4241680e+04
 2.0153879e+03 8.8054199e+02 6.5397690e+03 4.8592801e+02 1.2762729e+04
 9.3267266e+03 1.6348347e+04 1.2343329e+04 5.9062861e+03 1.0727955e+04
 1.1396142e+04 1.0006353e+04 3.2971500e+02 1.0778094e+04 4.0826431e+03
 1.9446029e+04 1.9354410e+03 3.2729104e+04 3.5588340e+03 2.4563564e+04
 2.0847061e+03 1.3637034e+04 1.1739042e+04 6.2614711e+04 6.3064980e+03
 5.5869932e+03 7.5142349e+03 1.9318230e+03 5.0558672e+03 1.3602330e+04
 5.2255352e+03 2.6453521e+03 5.4044009e+03 3.2550623e+04 1.0659204e+04
 7.4895300e+02 3.2434741e+03 4.4769512e+03 1.4749695e+04 9.6507898e+02
 3.3928012e+04 2.1107205e+04 1.0950984e+04 1.5468300e+02 5.7525298e+03
 2.9506321e+03 2.5020000e+03 5.7736709e+03 4.0778550e+03 1.6315623e+04
 3.5682749e+03 4.2827041e+03 6.8857202e+02 9.4124883e+03 6.4605962e+03
 7.3093500e+02 1.1755548e+04 2.0572461e+04 2.4360930e+04 7.0939888e+03
 6.9335459e+03 5.2270381e+03 1.4967018e+04 6.2381431e+03 6.9960508e+03
 1.9224360e+03 1.9827540e+03 1.0902240e+04 1.2124341e+04 6.3931050e+03
 6.9288838e+03 7.7309100e+02 2.6992800e+03 1.9304414e+04 4.6471318e+03
 9.4909951e+03 1.2395341e+03 1.1116440e+03 7.2158398e+02 1.6065720e+04
 1.4724360e+03 2.2025339e+03 3.5653148e+04 7.0599512e+03 3.9375000e+02
 1.4223960e+03 3.1674241e+03 7.4845171e+03 8.0970298e+03 7.2121318e+03
 1.2649743e+04 8.7552900e+03 2.0542383e+04 1.3023000e+03 6.7562012e+03
 7.7934601e+02 1.1821050e+03 3.8459367e+04 8.4169346e+03 9.3417930e+03
 1.0707786e+04 6.7090771e+03 7.5013202e+02 1.7379855e+04 9.0958502e+02
 2.0786760e+03 2.1323069e+03 1.1745990e+03 5.7529797e+02 1.1286495e+04
 1.5032700e+03 1.2886794e+04 1.1760210e+03 5.4972720e+03 5.5527301e+02
 1.3597605e+04 3.2956379e+03 8.7885723e+03 1.9974547e+04 1.1402100e+04
 1.7538184e+04 1.4122755e+04 1.0198143e+04 2.6871030e+03 2.6461621e+03
 6.1675649e+03 2.3935420e+04 8.8631367e+03 3.3026760e+03 4.4207999e+02
 1.2820590e+03 1.1647188e+04 5.9496118e+03 1.6075314e+04 6.3158102e+04
 5.7333418e+03 6.4805581e+03 1.3476249e+04 1.3629871e+03 1.1532519e+04
 1.3631697e+04 9.5064658e+03 2.9976841e+03 5.1036211e+03 5.9934601e+02
 7.2222842e+03 4.9901938e+03 2.9435491e+03 1.0286100e+04]
Feature: Total_trx
Tensor: [660. 572. 571. 568. 554. 523. 516. 498. 479. 459. 456. 426. 424. 416.
 408. 404. 401. 399. 397. 394. 389. 372. 364. 355. 354. 347. 343. 338.
 334. 326. 321. 319. 317. 315. 313. 312. 304. 301. 298. 295. 291. 290.
 288. 287. 286. 284. 280. 277. 276. 275. 273. 268. 267. 262. 260. 259.
 258. 255. 254. 252. 251. 249. 248. 245. 244. 243. 242. 241. 239. 238.
 237. 235. 233. 232. 229. 228. 225. 224. 223. 222. 221. 220. 219. 218.
 217. 216. 215. 214. 213. 211. 210. 209. 207. 206. 205. 203. 202. 201.
 200. 199. 198. 197. 194. 193. 192. 191. 189. 188. 187. 186. 185. 184.
 183. 182. 181. 180. 179. 178. 177. 176. 173. 172. 171. 170. 169. 168.
 167. 166. 165. 164. 163. 162. 161. 160. 159. 158. 157. 156. 155. 154.
 153. 152. 151. 150. 149. 148. 147. 146. 145. 144. 143. 142. 141. 140.
 139. 138. 137. 136. 135. 134. 133. 132. 131. 130. 129. 128. 127. 126.
 125. 124. 123. 122. 121. 120. 119. 118. 117. 116. 115. 114. 113. 112.
 111. 110. 109. 108. 107. 106. 105. 104. 103. 102. 101. 100.  99.  98.
  97.  96.  95.  94.  93.  92.  91.  90.  89.  88.  87.  86.  85.  84.
  83.  82.  81.  80.  79.  78.  77.  76.  75.]
Feature: Total_item
Tensor: [3381. 1880.  969.  889. 2372.  772. 1207. 1875.  993. 1438.  691. 1328.
 1206. 2521.  575. 1520. 6237.  561.  964. 1603. 3256.  869.  628. 1165.
 4118.  801.  660. 2023. 1869.  890.  625.  970.  937. 1787. 1048.  770.
  481.  428.  768.  472.  719. 1445. 4145. 4059.  965.  920.  900.  534.
 2263.  739.  589.  478.  800. 1684. 2357.  484. 1469. 1958. 2194.  644.
  767.  535.  435. 1144.  645.  581.  885.  646. 1382. 1212. 2026. 1478.
 1300.  454.  837. 1377. 1374.  636.  505.  968.  370. 2129. 1226.  871.
 1013.  677.  391.  325.  672.  888.  736.  670. 1129. 1474. 1210. 1161.
 2436.  577.  464.  418.  296. 1133.  726.  400.  794.  619.  887.  680.
  515.  287.  688. 1864.  398. 1211.  854.  389. 1337.  394.  913. 1459.
 1702. 1448.  423.  393. 1301. 3271.  384.  488. 1171.  567.  962. 1086.
  910. 1293. 1921.  437.  366. 1118. 1227.  572.  533.  632.  608.  491.
  251.  754. 1115.  986.  676.  724. 1295. 1014.  675.  412. 1036.  386.
  743.  576. 3939.  429.  522. 1660. 1565.  981. 1512.  734.  985.  549.
  314.  495.  420. 1532.  379.  893.  338. 1015.  301. 2869.  651. 1616.
 1195.  274.  365.  350.  823.  580. 1176.  511.  821.  527.  415.  413.
  822. 1317.  732.  585.  874.  661.  878.  387.  816.  297. 1529.  458.
 1192. 1471.  381.  348. 1619. 1163. 1611.  583. 1463. 1666.  952.  385.
  356. 1231. 1649.  461. 1066.  538. 2852. 1077. 1535.  291.  207.  547.
 1553.  796.  777.  835.  306.  310.  352.  448.  532.  759.  403.  344.
  703. 2050. 1172.  329. 1297. 2337.  933. 1274.  915.  183.  337.  654.
 1434.  307.  209.  267.  545.  480.  311.  354.  596.  468. 1157.  558.
  493. 2113. 1050.  498. 1028.  217. 1053.  313. 1012.  193.  245. 1400.
  233.  216.  390.  210. 1353. 1997.  304.  388.  652.  326.  617.  276.
  662.  975.  327.  826.  238.  320. 1201.  811.  280. 1146. 1189.  212.
  512.  786.  184. 1061.  998.  524.  303.  191.  258. 1723.  643.  248.
  187.  525. 1439.  224.  839.  709. 1101.  286.  611.  502.  185.  664.
  396.  462.  336.  790.  180.  789.  784.  275.  263.  921.  761.  926.
  242.  474.  566.  696.  288.  203.  824.  299.  733. 1296.  243.  255.
  932. 1398. 1017.  542.  341.  240.  223.  157.  529.  667.  704.  776.
  261.  649.  699.  457.  346.  232.  204.  663.  514.  820.  792.  257.
  312.  673.  298. 1137.  550. 1235.  471.  427.  689.  324.  383.  614.
  285.  206.  769.  504.  674.  506.  188.  987.  368. 1515. 1175.  902.
 1143.  208.  283. 1786. 1004. 1659.  977.  697.  422.  752. 1002. 1220.
  317.  978.  439.  200.  250.  397.  202. 1246.  360.  723.  160.  687.
  382.  633.  262.  612.  465.  222.  657. 1126.  246.  281.  169.  706.
  765. 1179.  641.  563.  220.  164.  345. 1949.  631. 1566.  603.  241.
 1470.  742.  168.  574.  227.  861.  523.  154. 1040.  361.  309.  152.
  330.  319.  229.  530.  573.  679.  247.  499.  943.  896.  355.  606.
  374. 1316.  225.  155.  268.  997.  271.  186.  289.  541. 1001.  903.
 1039.  833.  278.  256.  115.  239.  470.  178.  117.  459.  803.  698.
 1202. 1102.  162.  980.  433.  357. 1229.  335.  648.  879.  449.  996.
  235.  249.  731.  228. 1668.  165. 1365.  147.  333.  166. 1441.  489.
  901.  618.  745.  293.  182.  475.  219.  294.  124.  582.  593.  148.
 1815. 1062.  367.  856.  376.  705.  340.  305.  895.  146.  211.  339.
  961.  946.  264.  145. 1032.  778.  815.  774.  153. 1186.  989.  455.
  483.  509. 1396.  358.  137.  215.  510. 1867. 1214.  194.  466.  409.
  445.  813. 1437.  231.  161.  362.  451.  218.  501. 1443.  277.  172.
  979.  728.  432.  519.  269. 1204.  668. 1109.  176.  199.  322.  702.
  830.  252.  621.  205. 1432.  831.  834.  375.  159. 1303.  773.  144.
 1621.  300.  988.  876. 1279.  482.  414.  197.  170.  369.  452.  290.
 1242.  171.  174.  995.  112.  517. 1221.  421.  782. 1150.  843.  460.
  624.  497.  479. 1131. 1335.  410.  328.  221.  456. 1181.  949. 1268.
   84.  343.  477.  444.  121.  840.  129.  332.  791.  436.  132.  167.
  441. 1197.  318.  425.  103.  347.   99.  130. 2231.  177.  111.  513.
  690.  142.  588.  715.  579.  123.  122.  805.  113.  151.  295.  116.
  555.  244.  377.  559.  620.  363.  364.  653.]
Feature: Total_unique_items
Tensor: [ 687.  323.  218.  166.  644.  227.  508.  373.  172.  818.  182.  776.
  163.  252.  138.  355.  840.  207.  176.  402.  810.  161.  224.  367.
  551.  204.  319.  381.  420.  585.  148.  372.  279.  421.  275.  294.
  206.  118.  191.  112.  277.  304.  414.  537.  622.  347.  336.  193.
  186.  461.  195.  179.  208.  267.  519.  451.  120.  246.  540.  478.
  316.  192.   70.  500.  165.  175.  296.  216.  525.  117.  566.  484.
  506.  299.  350.  428.  343.   76.  701.  358.  412.  162.  145.   77.
  190.  245.  139.  147.  146.  426.  693.  234.  328.  606.  144.   88.
  397.  417.   94.   78.  401.  311.  203.  150.  433.   53.  352.  563.
  496.  390.  121.  364.  860.  342.  128.  362. 1023.   93.  220.  610.
  313.  383.  379.  408.  721.  173.   68.  423.  511.  196.  302.  243.
  254.  300.  436.  283.  580.  415.   86.  305.  233.  238.  122.  998.
  141.  125.  526.  564.  425.  431.  331.  132.  601.  387.  135.  466.
  136.  649.  291.  635.  156.  384.  137.  124.  293.  171.  483.  134.
  276.  340.  169.  232.  326.  345.  266.  363.  178.  376.   57.  579.
  403.  151.  608.   90.  140.  627.  554.  237.  734.  361.  507.  757.
  108.   91.  873.  354.  595.  157.   55.  258.  573.  223.  255.  185.
  142.  230.  183.   80.  399.  546.  771.  389.  527.  468.  231.  272.
  509.   72.  101.  143.  214.  215.  129.  458.  646.  187.  280.  398.
   73.  536.  159.  439.  181.   95.  149.  329.  104.  490.  131.  152.
  382.  177.  386.   89.   60.  346.   49.   61.  394.  493.  155.  103.
  679.  239.   87.  242.  502.   75.  380.  317.  325.  205.  263.  244.
  282.  339.  180.   67.  213.  259.  188.  174.  241.  113.  116.  249.
  260.  515.   46.  123.  473.  393.  119.  133.   98.   84.   39.  256.
  341.  322.  335.  160.  153.  114.  269.  111.  310.  450.  210.  109.
  235.  290.   96.  392.  168.  236.  226.  219.  495.  158.  324.  378.
  285.   79.  248.  593.   85.  630.  274.  308.  407.  440.  154.  334.
   97.  598.  229.   42.  321.  303.  271.  247.   63.  200.  567.  501.
  437.  253.  438.  422.  314.  883.  514.  265.   81.  388.  198.   50.
  643.   74.  281.  457.   99.   66.   16.  197.   54.  353.  225.  395.
   17.  199.   32.  301.  513.  418.  444.  307.  662.  452.  424.  170.
  529.  106.   59.  617.  429.  574.  333.   92.  105.   47.   35.   64.
  672.  467.  222.   33.  130.  287.   58.  228.   31.  273.   65.  453.
  479.  441.  427.  202.  465.   36.  209.  456.  743.   83.  535.  520.
   40.  360.  126.  351.  619.  375.  261.  107.  270.  521.  348.  406.
  447.  652.  250.  560.  356.  708.   24.  289.  833.  315.   25.  201.
  682.  240.  184.   82.   41.  518.   44.  221.  257.   38.  212.  102.
  725.  298.  368.   37.   51.  531.  416.  309.   19.]
Feature: Total_unique_subclasses
Tensor: [236. 116. 101.  78. 200. 198. 139.  90. 240. 256.  84. 130. 155. 249.
 111.  85. 187. 274.  83.  97. 142. 219. 148. 160. 161. 210.  66. 166.
 182. 109. 133. 123.  62.  57. 132. 117. 201. 213. 156. 168. 141.  88.
  75. 181.  93.  77.  99. 134. 207. 192.  76.  98. 211. 177. 143.  95.
  33. 197. 122. 110. 216.  53. 194. 174. 176. 103. 175.  67. 171.  32.
 221. 164.  68.  51.  74. 217.  69. 151. 220. 128.  70.  82.  39. 169.
  42.  36. 159. 135. 102. 183.  34. 157. 184. 172.  60. 290.  92.  64.
  45. 296.  49. 237.  50. 170. 235.  96. 195.  30. 215. 153.  58. 154.
  81. 113.  59. 289.  63. 158. 165. 185. 149.  72.  40.  61. 189. 228.
 144. 108.  86.  87. 137. 191. 150.  89. 119. 145. 131. 138. 146.  80.
 208.  48.  27.  73. 152. 223. 136. 243. 255. 120.  56.  79.  38. 212.
 105.  94. 230. 127.  35. 125.  37.  47. 115.  71. 251. 167. 199.  41.
 186.  65. 129. 121.  28. 241.  52. 106. 104. 100.  43.  44. 126. 233.
  23.  55.  15. 162. 118. 193. 218.  54.  24.  26. 206. 178. 276. 231.
 190. 163. 112.  31.  12. 173.   9.  91. 188. 140. 196.  29. 114.  13.
  14. 205. 107. 180. 179.  17. 281. 202.  19. 124.  46. 224. 203.  11.
 284.  16. 238.  25. 226. 209.  22.]
Feature: Total_unique_subdepartments
Tensor: [68. 42. 41. 34. 66. 55. 69. 48. 43. 84. 33. 36. 56. 39. 60. 75. 47. 77.
 38. 40. 54. 74. 44. 50. 62. 70. 30. 63. 51. 61. 53. 35. 24. 49. 67. 71.
 52. 58. 45. 19. 59. 46. 31. 57. 65. 17. 26. 29. 21. 22. 28. 20. 27. 64.
 85. 92. 76. 79. 32. 37. 13. 16. 25. 18. 81. 23. 72. 10.  9. 11. 14. 15.
 78.  7. 73.  6. 87.  5.  8.]
Feature: Min_spend
Tensor: [0.    0.54  0.36  0.054 0.189 0.414 0.351 0.45  0.117 0.558 0.288 0.846
 0.162 0.495 0.09  0.855 0.027 1.035 0.468 0.405 0.675 0.531 0.756 0.9
 0.27  0.18  0.009 0.423 0.342 0.144 0.126 0.315 0.252 0.081 0.306 0.918
 0.207 0.828 0.738 0.225 0.477 0.261 0.792 0.099 0.279 1.044 0.693 0.432
 0.72  0.513 0.072 0.369 0.216 1.026 1.755 1.35  0.396 0.378 0.036 0.171
 0.153 0.333 0.873 0.612 0.594 1.116 0.639 1.107 0.666 0.711 0.486 0.585
 1.575 0.81  1.125 0.504 0.657 1.8   0.324 0.621 0.063 1.089 0.927 1.305
 0.603 0.981 0.576 0.882 0.441 2.34  0.999 0.801]
Feature: Max_spend
Tensor: [1.6155000e+03 8.0352002e+02 2.7288000e+02 9.8550003e+01 3.4425000e+02
 1.0350000e+02 1.0800000e+03 5.7109497e+02 4.4910001e+02 1.7887500e+04
 1.9800000e+02 5.2125121e+04 6.2955002e+01 5.8158002e+02 4.0410001e+02
 9.6408002e+02 8.3531250e+03 5.0139001e+02 2.2302000e+02 4.3739999e+02
 9.0000000e+03 1.2780000e+03 2.2387500e+02 5.1066002e+01 1.3795200e+03
 3.5910001e+02 2.5848001e+02 2.3850000e+03 6.9254999e+02 2.1357945e+04
 1.0120950e+03 1.6159500e+02 8.8695000e+03 2.4259500e+02 1.9542599e+02
 1.4039999e+02 4.9950000e+02 6.1200000e+02 7.3980003e+01 1.2600000e+02
 4.1849998e+01 1.9782001e+02 2.6639999e+02 5.3208002e+02 8.1000000e+02
 7.4358002e+02 4.7137500e+02 2.8309500e+02 1.8000000e+02 1.2456000e+03
 1.1599200e+03 8.4941998e+02 1.1862000e+02 1.3139999e+02 3.2359500e+02
 5.1637500e+02 4.8438000e+02 4.0320001e+02 7.1639999e+01 2.9743201e+03
 4.3560001e+02 8.4375000e+02 7.9019997e+01 1.5349500e+02 1.6200000e+02
 1.4539500e+02 8.0459999e+01 2.7539999e+02 1.1647800e+03 1.0746000e+02
 1.2643199e+03 3.3750000e+02 1.4382000e+04 7.7422498e+02 2.4989400e+02
 3.3782401e+02 1.7010001e+02 1.9057500e+02 1.4543550e+03 4.0230000e+01
 9.7465503e+02 4.8195000e+01 5.9453998e+02 1.2406500e+02 2.0466000e+02
 3.8717999e+02 5.0355000e+01 2.4637500e+02 3.0555000e+01 4.3875000e+02
 1.7550000e+02 1.0804500e+03 4.5855000e+01 1.3315500e+02 1.4328000e+02
 5.6996997e+02 3.6382501e+02 1.3567500e+02 1.8855000e+03 1.2960000e+03
 1.2420000e+02 2.1582001e+02 8.7750000e+02 7.2900000e+03 2.7945001e+02
 4.4099998e+01 1.5750000e+02 3.9409738e+04 1.1745000e+02 4.2637500e+02
 6.0750000e+01 2.0700001e+01 1.1844000e+03 4.1220001e+02 3.5639999e+02
 3.6097198e+02 8.9887500e+02 5.1678003e+02 8.0550000e+02 7.1820000e+01
 1.9845000e+02 5.9400000e+02 2.0691001e+03 5.3887500e+02 8.3834999e+01
 1.4073750e+03 6.5245502e+02 5.0220001e+01 5.4000000e+02 7.1550000e+02
 5.2699500e+02 5.2209003e+02 5.4647998e+02 8.0482501e+02 6.4638000e+02
 5.0328000e+02 1.4175000e+02 6.0255001e+01 8.9775000e+02 9.4770001e+02
 5.3909998e+02 1.7514900e+02 2.2860001e+02 1.2240000e+03 1.4382001e+02
 1.3729500e+02 5.6879999e+02 3.0167999e+02 1.2600000e+03 1.0422000e+02
 4.0932001e+02 1.1323800e+03 1.1137500e+03 8.9099998e+01 4.0500000e+02
 8.5680000e+01 3.8815201e+02 3.1387500e+02 1.0113750e+03 4.4955002e+01
 8.2620003e+01 4.6979999e+02 6.2577000e+01 1.0395000e+02 1.9278000e+02
 7.9128003e+02 1.3950000e+02 1.4619600e+03 6.2099998e+01 5.0714999e+02
 6.2550000e+02 1.7262000e+02 5.3099998e+01 1.2895200e+03 8.0099998e+01
 3.8664001e+02 3.7440000e+03 1.3410001e+02 8.9550000e+02 2.0862000e+02
 8.0595001e+01 7.2900002e+01 1.8900000e+02 2.5020000e+03 5.8320001e+02
 1.9953000e+02 9.6794998e+01 1.7280000e+02 2.1222000e+02 6.4440002e+01
 5.8500000e+02 3.0510001e+02 2.4120000e+02 5.0220000e+03 2.9160001e+02
 5.7312000e+02 9.8550000e+02 5.3550000e+02 3.1607999e+02 6.3072000e+04
 5.3306999e+01 1.5462000e+02 4.4887500e+02 3.7439999e+02 6.9750000e+01
 3.9738599e+02 2.6239499e+02 4.4437500e+02 2.5272000e+03 1.2939750e+03
 5.1479999e+02 3.8137500e+02 2.4839999e+02 2.1937500e+02 4.8289499e+02
 4.6619999e+01 3.6000000e+02 7.5537000e+02 7.1279999e+02 1.7982001e+02
 1.2608100e+02 1.0678500e+02 1.8792000e+03 3.9375000e+02 3.2238000e+02
 9.5400002e+01 6.3102600e+02 7.8637500e+02 4.1356802e+03 2.4408000e+02
 7.9199997e+01 1.0425601e+03 2.8728000e+02 1.4191200e+03 6.8832001e+02
 6.7189502e+02 4.1895001e+02 1.8180000e+02 6.7500000e+01 1.5767999e+02
 2.4559199e+03 9.0000000e+01 1.6767000e+02 1.1520000e+02 1.9439999e+02
 1.0980000e+02 5.8409998e+02 1.1250000e+02 5.3207098e+02 1.2637800e+02
 6.8620502e+02 5.2650000e+02 1.4580000e+02 2.0286000e+03 8.3654999e+02
 2.0088000e+02 2.0700000e+02 4.5000000e+01 1.6119000e+02 1.5525000e+02
 2.6865000e+01 8.0959497e+02 8.2312201e+02 3.0642300e+02 7.9379999e+02
 4.8555000e+01 2.2950000e+02 8.4599998e+01 1.2109500e+02 7.4749500e+02
 2.2320000e+02 2.3652000e+02 2.4300000e+02 5.6137500e+02 1.2942000e+02
 7.0199997e+01 1.7739000e+02 4.0387500e+02 6.5609998e+02 2.4282001e+02
 2.8656000e+02 2.8979999e+02 1.0800000e+02 5.5755001e+01 1.7779500e+02
 2.2843799e+03 1.8589500e+02 6.0750000e+02 2.4299999e+01 2.6910001e+02
 3.3048001e+02 4.6800000e+02 7.3125000e+01 1.1627550e+03 2.5069501e+02
 1.5112800e+03 3.1679999e+02 2.6729999e+02 4.1625000e+02 2.5920001e+02
 9.3109497e+02 2.8090799e+02 1.6969501e+02 3.0375000e+03 8.7840002e+02
 4.3312500e+02 4.0455002e+01 2.2500000e+03 1.6758000e+03 2.1872701e+02
 2.8800000e+02 2.6945999e+02 2.4750000e+02 1.0303199e+03 1.7910001e+02
 2.2639500e+02 3.2039999e+02 5.4450001e+01 5.6088000e+02 3.0420001e+02
 2.8023300e+02 4.3020000e+01 2.0079900e+02 1.2672000e+03 9.3150002e+01
 4.3699500e+02 1.0999800e+03 4.2020099e+02 4.4928001e+01 1.1610000e+02
 2.2517999e+02 7.0559998e+02 3.0600000e+02 1.5890401e+02 4.2750000e+02
 4.8599998e+01 7.0875000e+01 1.8123750e+03 8.9447400e+02 2.5560001e+02
 6.4800003e+01 1.3122000e+03 1.5616801e+03 2.9564999e+02 3.8610001e+02
 3.6409500e+02 3.4020000e+01 1.2157200e+02 1.5863400e+03 6.0750000e+03
 6.1154999e+01 1.8810001e+02 1.4377499e+02 4.2839999e+02 4.9679999e+02
 5.6700000e+02 2.3895000e+02 3.7260001e+02 9.7199997e+01 2.6550000e+02
 1.2888000e+02 2.1217949e+03 2.7000000e+02 2.1771001e+02 2.7013501e+02
 1.4947200e+03 9.6479999e+02 4.9455002e+01 1.5565500e+02 5.1557397e+02
 1.9800000e+03 1.3090050e+03 1.2458250e+03 1.3972501e+02 3.0942001e+02
 1.1925000e+02 4.9500000e+02 1.2919501e+02 1.0915200e+03 1.8333900e+02
 1.0710000e+02 6.1559998e+02 3.2400000e+02 8.2800003e+01 6.1020000e+01
 1.6098750e+03 7.9200000e+02 5.8174199e+03 9.4454999e+02 9.8099998e+01
 3.6720001e+02 2.3400000e+01 2.6365500e+02 1.3387500e+02 4.4550000e+02
 5.6870998e+01 6.8040002e+02 1.8603000e+02 1.6214400e+02 2.5757999e+02
 9.4500000e+01 1.8225000e+01 9.6300003e+01 1.9381949e+03 3.8475000e+02
 2.9929501e+02 2.8439999e+02 5.3955002e+01 1.0449000e+03 1.7955000e+03
 5.7599998e+01 5.1785999e+02 4.4549999e+01 1.0348200e+02 2.8782001e+02
 4.9387500e+02 9.9000000e+01 1.0489500e+02 5.9355000e+01 1.0620000e+02
 1.0260000e+02 1.6645500e+02 9.6840002e+02 2.7939600e+03 4.2984000e+02
 3.0739499e+02 6.1875000e+01 1.5031799e+02 1.8539999e+02 9.3712500e+02
 6.4620003e+01 2.9520001e+02 8.6220001e+01 1.9380600e+02 3.3210001e+02
 5.2531201e+02 1.9399500e+02 6.4728003e+02 3.5820001e+02 2.4752699e+02
 9.1540802e+02 8.0055000e+01 1.5795000e+02 5.6609998e+02 6.4754997e+01
 1.1448000e+02 2.6463599e+02 8.7317999e+02 5.9534998e+02 1.2034080e+03
 2.5182001e+02 1.4364000e+02 6.4476001e+02 5.0062500e+02 2.8125000e+02
 6.2072998e+02 1.6182001e+02 1.5300000e+03 2.0700000e+03 1.8420300e+02
 2.1923100e+02 2.2500000e+02 3.1526550e+03 3.0916800e+02 1.3364999e+02
 3.9419998e+01 1.1502000e+02 1.1655000e+03 1.1142000e+02 9.9764999e+01
 4.3375500e+02 2.3750999e+02 1.8630000e+02 6.2887500e+02 8.6372998e+02
 4.4872198e+02 2.0610001e+02 2.9119501e+02 1.0764000e+03 6.8220001e+01
 4.6575001e+01 2.2503600e+02 8.8110001e+01 6.6240002e+02 2.4555600e+02
 3.1995001e+01 2.2967999e+02 3.1680000e+03 5.2541998e+02 4.5562500e+02
 6.7878003e+02 9.8177399e+02 3.5478000e+02 2.8350000e+02 1.0148400e+02
 1.5822000e+02 2.2890601e+02 2.1600000e+01 3.8250000e+02 2.9610001e+02
 9.2018701e+02 9.3123001e+01 4.5792001e+02 5.2154999e+01 3.2673599e+02
 2.4417000e+02 1.6902000e+02 3.3906601e+02 2.3382001e+02 4.0297501e+02
 3.4335901e+02 3.7754999e+02 8.3699997e+01 1.9125000e+02 7.4330103e+02
 2.1829500e+02 2.0655000e+03 1.6560001e+02 3.0209399e+02 2.4255000e+02
 3.3992999e+02 2.1019501e+02 5.4000000e+01 7.8042603e+02 7.2900000e+02
 1.8604800e+02 1.6380000e+02 1.5860160e+03 4.1282999e+02 1.8459000e+03
 8.2521004e+01 2.3310001e+02 4.5198001e+02 7.9468201e+02 9.1871997e+02
 6.3288000e+02 2.1528000e+02 3.2140801e+03 3.8029501e+02 1.2582000e+02
 1.5120000e+02 2.9691000e+02 3.8025000e+02 2.0209500e+02 5.0400000e+02
 2.2173750e+03 1.4400000e+02 3.3300000e+02 2.9565001e+01 4.2120001e+02
 4.2525002e+01 2.1328200e+02 1.6119000e+03 8.3700000e+02 1.4256000e+03
 9.3419998e+01 3.0923999e+02 7.6500000e+01 4.9045499e+02 3.2121899e+02
 5.1889951e+03 1.4086440e+03 5.6250000e+02 1.8144000e+03 6.8850000e+02
 1.0942200e+02 2.6622000e+02 5.2200001e+01 2.4480000e+02 6.9300003e+01
 1.7212500e+02 4.3064999e+01 8.6112000e+02 2.0655000e+02 1.0062000e+02
 8.1675003e+01 2.6262000e+02 8.6400002e+01 9.0666000e+01 1.9755000e+03
 3.5820000e+01 6.4817549e+03 5.1750000e+01 2.6279999e+02 1.4310001e+02
 7.1909998e+02 1.7820000e+02 2.1239999e+02 2.5891201e+03 3.7125000e+02
 2.0137500e+02 1.0935000e+02 3.1310549e+03 2.0520000e+02 8.9955002e+01
 1.9062000e+02 5.0625000e+01 5.8455002e+01 1.3219200e+03 2.2752000e+02
 2.1465000e+01 3.3462000e+02 2.3713200e+02 1.5852600e+02 1.7369550e+03
 7.9825500e+02 3.4542001e+02 7.7597998e+02 1.4760001e+02 1.0782000e+02
 3.3839999e+02 4.5319501e+02 1.9764000e+03 2.2011301e+02 1.3968000e+03
 7.8847198e+02 2.3625000e+02 1.3490100e+02 8.9582397e+02 5.9400002e+01
 2.8079999e+02 3.2670001e+02 2.8799999e+01 7.2827998e+03 4.8559500e+02
 1.5265800e+02 7.0200000e+00 8.9909998e+02 7.8300003e+01 8.8695000e+01
 1.0897200e+02 2.3355000e+01 1.3671000e+03 3.2541299e+02 1.6402499e+02
 5.0220001e+02 3.1410001e+02 4.1022000e+02 1.5115500e+02 2.0025000e+02
 9.4724998e+01 1.0125000e+02 1.0687500e+03 4.2300000e+02 1.2220200e+02
 1.6200001e+01 1.2150000e+02 1.0080000e+02 2.8998001e+02 5.1767999e+02
 3.0083401e+02 3.4560001e+02 1.7100000e+01 8.2620001e+02 2.6689499e+02
 1.9314900e+02 5.4917999e+02 7.5419998e+01 1.4022000e+02 2.5650000e+01
 1.9422000e+02 6.2283600e+02 2.0286000e+02 2.7360001e+02 1.0617750e+03
 5.0179501e+02 2.2885201e+02 1.0324800e+02 7.1887500e+02 1.8225000e+02
 1.5795000e+01 2.7807300e+02 8.1000000e+01 3.8655000e+03 1.1313000e+02
 1.5255000e+03 1.0368000e+03 3.9239999e+02 8.6564697e+02 3.2220001e+01
 1.3770000e+02]
Feature: days_since_last_purchase
Tensor: [  0.   2.   1.  32.  37.  82.  36.   4.  12.  40.   3.   9.   5.   8.
  34.  16.  51.  43.  20.  13.  26.  45.  21.  35.  17.  22.  15.  42.
  46.  30.   6.   7.  59.  41.  69.  44.  57.  28. 134.  10.  39.  38.
  95.  98.  88.  23.  11.  58.  25.  66. 163.  90.  54.  14.  19.  24.
  52.  50.  72.  62.  33.  64. 140.  49. 130.  76.  48.  89.  31. 170.
  93. 139.  56.  67.]
Feature: days_since_first_purchase
Tensor: [241. 240. 239. 235. 229. 236. 178. 234. 223. 231. 226. 208. 232. 228.
 237. 214. 157. 222. 194. 238. 166. 188. 230. 233. 193. 177. 221. 148.
 164. 215. 185. 219. 200.  70.  77. 147. 218. 174. 220. 227. 199. 196.
 213. 224. 173. 225. 169. 211. 126.  85. 195. 170. 165. 206. 205. 163.
 192. 144. 113. 149. 139.  55. 210. 159. 132. 204. 136. 175. 191. 197.
 201. 189. 158. 168. 212. 127. 125. 146.  80.]
Feature: spend_per_trx
Tensor: [  96.40979     31.202213    14.014875    11.348715    31.50489
    8.47196     16.48718    109.93869     12.721228   577.483
   12.039294  1110.413        6.3701844  114.67097      9.410222
   57.868984  1011.41974     17.11263     18.304485    51.58535
  480.15768     24.953485    15.53978     11.015491   349.28323
    9.652797    11.705679   199.2242     177.39641    608.7119
   18.864027    29.09225    313.04477    109.12301     33.491844
   15.285309    32.65141      9.347135    10.724422     5.0271144
   14.162886    22.320686    35.81448    127.115715   515.1252
   72.96088     56.11518     37.113743    13.993261    26.489319
  167.3451      28.122875    10.581491    14.618822    45.1057
  110.65678    171.47838     13.8666935   12.653316   367.98944
   66.798065    55.169598    21.400112    17.335272     7.1070232
   67.36725     10.827105    23.075966    92.251816    18.329128
  111.408424     8.383623   291.32718    195.67131     55.34571
   62.317394    10.573178    32.51209     54.817734   118.46232
    8.916024     6.7155604  105.312485     9.109947   182.51927
   54.654343    29.650408    87.781685     6.895382    10.173615
    5.9896693   58.756084    52.847923    42.869846    10.754165
   30.542439    45.02862     69.90339     49.16244     58.50927
  304.8186      34.165028     7.5250263    9.90424     14.720022
  334.99976     29.41991      7.622475    22.287107   603.62396
   27.09615     67.248856    14.562531    93.457306     3.6763973
   54.548916   106.98449     18.60524     77.57311    117.78831
   13.209802   116.391815    11.860583    22.206583   109.16217
  183.17299    101.05431     23.468761    29.472855     6.9158874
  184.63306    538.6923       8.525218    45.589394   178.49538
   40.40505     83.442276   112.89965     81.778915   153.7688
  146.83107     21.339306     6.7984242  108.401886   149.61478
   14.485873    61.87263     37.115555    60.480663    15.889389
    5.0395546   81.45245     79.16921     88.83206     48.751656
   27.8703      74.3746      69.19046     82.08727      9.969136
  117.68495     11.843318    40.090908    50.395798    13.265119
  625.0906       7.6287527   16.997736    83.26819     20.764547
  100.362236   123.251656   114.48271    132.78499     45.665375
  102.28394     51.850353     6.9695325   14.805194     9.6592865
  137.73312     29.422321    57.28319      7.9585576  127.36254
    6.4548197  384.1923      52.859337  1216.1237       8.19185
  150.99315     60.232124    10.731067     9.62276     20.187151
  284.61584     64.62435    115.73778     12.33445     91.38843
   30.54244     20.041323    12.954681   147.84776    116.4441
   51.080368    30.716064   699.18506     44.312286   159.72353
   91.40819    105.62128     32.259453   774.5375       8.798053
  121.26621     35.932106   117.752686    61.92397     19.686441
   18.177195     9.416929   185.58798    126.620415   124.5698
  235.43262    242.62157    243.03703     56.29961     33.313446
    8.019759    98.12543    109.560036    85.60593    120.14335
    8.647309    21.177217   208.48143    199.00618    148.12428
   16.671667    13.284448    15.80182      6.809344    80.39227
  266.01068    105.74406     74.31357     76.80385     35.901398
   41.089954   283.34402     33.436768   112.29904     23.223497
   22.542133    24.728216    80.833015   226.42744    165.29106
  100.473114   139.74289    141.02977     78.27254    111.22345
  117.39851     79.795815     4.4806557   13.679824    55.949528
   98.74188    430.5787      16.307703    13.749987     7.253408
   54.42134     29.53639     14.274477    30.44826     25.30872
   25.56054     79.97268     15.405342   316.99527     22.211637
   74.15112     26.721182    16.295898   299.28204    467.21262
  115.20912    159.58029      8.382612   136.64706     36.031807
  104.97125     12.787274    36.641422    44.289745    17.783379
   53.94842     95.89376      4.743683    22.916876    23.147438
   28.305813   208.727      189.36707     28.032938    19.172958
   66.76288     23.079966    25.088198    19.981901    24.688395
   71.67556    130.28615     10.202324    24.175776    94.627785
   19.246084    31.585724    11.6748      27.20835     29.143158
   76.8609      94.179924    40.713234   164.13911    141.42181
   10.218367    18.800417    48.55202    102.094696    13.96663
    8.359957    75.93522    540.50696    145.44847     58.77788
   20.856375     5.402184    56.28951     16.630808   330.74707
   95.47414     21.428       11.677934   116.354866    42.71887
  436.74954      8.037      156.1274      61.561333    84.76455
   49.43633     20.65097    100.68515     58.97964     60.010307
   59.070206    77.16157     75.75873     69.663       28.16393
    9.421977    11.363221   360.87418     14.438886   244.23224
  100.25321    273.8605      50.367046    11.051792    38.685806
   67.78994    103.64012     21.14647     10.619654   162.59686
   15.663558    68.38207     45.680977    13.399101    95.842545
   17.884687    71.67234      7.5646405  116.13536      5.2302756
  151.16925    299.49762     12.488031    16.969606    65.98593
  142.95493    197.7265     222.595       33.10157     14.583143
    7.0018573   11.355143    27.605072   247.01979     90.214714
   61.255154    93.20724     17.646408    91.1052      11.27628
   30.787992   216.14429     71.61595     49.19047     51.125443
   19.711088    21.06029      8.570395    68.14234     13.879814
  120.09426     66.51278    301.86        74.441345    20.5065
   18.346352    33.542927   117.00699     11.24167    138.247
  115.1306      33.5994     474.925       27.347324    19.373924
  304.7232      11.439525    40.16685     45.30025     26.675093
   71.71435     34.176403    86.197426    57.044518    97.24645
   67.33647     14.341154    79.332306    11.947616   785.71344
  117.32769     22.992       86.52892     45.028385   186.52077
  171.48956    194.48201     86.74603    341.15363    690.5874
    5.544939    74.2813      60.063576   336.49725      5.9482956
  179.50171    702.2221     251.77211    142.52945     40.91329
  233.20839     78.50826    103.1482     248.9333      15.087106
  267.85226     36.930344   172.95276     46.807713     8.607938
   34.39784    164.28528     34.993526    10.998723   289.21954
   23.301325    19.634838   127.75305     16.725649     9.8588915
  153.39413    106.18224    114.77579     26.44151    788.76587
   83.40047     31.211836   622.71985     55.32439     24.099873
    8.185336    79.09036     49.53289    180.8768      21.116146
  107.919495    16.7599      56.12433    129.06859      9.02989
  262.70654    124.51426    128.31218     99.626915    54.011333
  164.52017     18.057167    18.381166     6.692       38.063416
 1126.2585      75.757835    26.362      244.71567     48.15775
   15.596833   168.8267      29.708916   728.02344    128.5031
    7.639654   208.61597     10.813037   121.804825   350.99655
   97.726204    19.255121    15.876336     5.3418784  162.84415
  100.09346     33.507       13.066066    11.056374    76.75663
  110.4204      26.737556    14.792858     9.884293    12.538104
   41.49416     24.55803     87.28072     76.501884   212.14645
    9.650828    22.725172    69.657684   200.35132     78.1116
   75.47383     14.9719715  176.44705    116.26457    105.3948
   43.100914   209.72324     10.952143     5.4988284   36.306347
   73.0054     300.22632     80.67617     15.93225     71.72048
  133.39886    273.59317     43.99321     24.001268     8.582592
   26.468475   102.59676     82.24244    136.74844    103.713295
  262.2558     271.20154    106.160416    38.593224    61.929176
   14.255388    11.525735    95.71853     56.12409      9.942617
   35.172176     6.2244706   91.86794     81.1133     108.04536
   96.334854   214.51535     93.48706    370.98706     10.644149
  146.91795     58.138397    23.425663   141.11082    157.73293
   18.03395     50.95978     98.34558    143.4388      66.42288
  176.88663     74.99466     21.63078     49.67424    138.3687
   40.29066    249.14445     35.16073    728.0223      14.916636
   59.514454    27.484       14.823      193.49873     13.0914545
   64.45591     61.869274   286.36972     60.114635   325.60532
  173.90443     15.284388    34.93653    100.68364      4.664847
  427.03192      8.056469    54.650204    16.742228   282.1101
  137.59572     33.393898   179.40489    118.25044    128.03177
   14.124562   188.65941     52.902374   118.261406    26.637562
   10.407469    83.19169     64.11947     13.158093    75.49446
    6.370863   134.24655     77.05203      6.839526   300.4108
  147.7135      24.65081     54.859547   556.92737     92.53383
  157.96136    110.71942    105.78458     23.30441    145.62929
  154.26335     80.66451     16.719128   160.82846     80.96208
   50.82635    110.30965     90.521805    75.55136    152.94542
    5.848085    41.62481     37.69296    332.31494     30.895548
  116.89887     20.805775    62.74326     17.17413     61.080193
  193.58554     33.239902   154.34662     57.529644   163.81277
   23.958967    23.294544   118.37935    136.91397     30.042294
   80.88261     15.7028475  345.5821     135.75356    146.38255
  261.5444      27.52601    103.35424      8.433692   212.66534
  177.2466     136.90187    127.553535     9.3634615  342.84253
   17.398384   153.78221     79.44023     55.485397   350.9922
   63.4542     507.6457      24.6629      81.9966     221.3292
   98.8533     204.4977       5.7945     180.1818      19.241
  201.241      209.6775      98.814       85.7879     732.1047
  137.7093      40.3046      34.1901      50.2922     145.1268
   53.6129     126.31884     24.945776   117.05036    154.3686
  132.38545    402.66434     35.53564     91.13936    122.42073
  240.91028     11.755416    83.92255     60.268806    13.61925
   63.04582     48.494762    57.24041     12.191011   531.1069
  222.73088    230.81175     10.67942    313.94098     15.876307
    7.157966    24.451977   191.53452     36.566284   459.91873
  265.23932     84.843414    73.54252    105.866486   332.35562
   17.977345    57.510933    25.989723   464.9764     102.50669
   82.09748     71.022514   320.07776     87.012314    22.795862
   48.55563     19.153465     7.9930463   48.84028     92.25011
   87.242966   235.21239     24.829535    56.971466    40.70323
   18.116686    83.31729     12.4332905  139.04675    201.2604
  114.22821    315.5243      48.210884    18.972635    62.88861
  248.01692    388.60876    167.60648   1001.7247      34.89565
   12.573635    30.851152   197.22197     15.818824    12.700059
  236.98196     54.281963   199.13474     71.12775    171.77528
  102.657646   732.69696     56.899178    64.55593     34.987286
   18.906643   575.0038      52.247463    97.84403     76.99586
   74.755196    71.85091     63.507793   158.74493     71.76329
  113.233665    70.08799    412.37665     26.141314     9.765
  180.03275     15.791964     9.953133    94.63825    412.55035
   24.281784    10.60894     79.75328      5.925951   155.64304
  113.74057    199.37009    150.5284      72.02788    164.53427
  130.82872    138.97734    122.028694     4.0209146  131.44017
   49.78833    237.14671     23.60294    404.063       43.936222
  303.25388     25.737112   168.35844    144.92644    773.0211
   77.858       68.97522     92.76833     23.849667    62.41811
  167.93        64.51278     32.65867     66.721      401.85956
  131.59511      9.246333    40.04289     55.271      182.095
   11.914556   418.86432    260.58276    135.19733      1.9096667
   71.906624    36.8829      31.275       72.17089     50.973186
  203.94528     44.60344     53.5338       8.60715    117.6561
   80.75745      9.136687   146.94435    257.15576    304.51163
   88.674866    86.66933     65.337975   187.08772     77.97678
   88.55761     24.334633    25.098152   138.00304    153.47267
   80.92538     87.70739      9.785962    34.168102   244.35968
   58.824455   120.139175    15.690304    14.071443     9.133975
  203.36354     18.63843     27.880177   451.3057      89.36647
    4.984177    18.235846    40.608       95.955345   103.808075
   92.463234   162.1762     112.24731    263.3639      16.696154
   86.61796      9.991615    15.155192   493.06882    107.909424
  119.76658    137.27931     87.13087      9.741974   225.7124
   11.812792    26.995792    27.692299    15.254533     7.4714026
  146.57785     19.522987   167.36096     15.273       71.39314
    7.2113376  176.59227     42.800495   114.1373     259.4097
  148.07922    227.76862    185.82573    134.1861      35.356617
   34.81792     81.15217    314.93973    116.620224    43.456264
    5.816842    16.869198   153.25247     78.28437    211.51729
  831.02765     75.43871     85.2705     177.31906     17.93404
  151.74367    181.75597    126.75288     39.96912     68.04828
    7.99128     96.29712     66.53592     39.24732    137.148    ]
Feature: Items_per_trx
Tensor: [ 6.  4.  2.  5.  3. 16.  9. 12. 14.  8.  7. 11. 10. 21. 18. 15. 13. 19.
 20. 17. 29.]
Feature: Unique_items_per_trx
Tensor: [ 2.  1.  3.  4.  5.  6.  9.  7.  8. 11. 10.]
Feature: Member_id
Tensor: [b'124334' b'6765190' b'12' b'3902052' b'168740' b'6450644' b'4562'
 b'51972' b'284' b'44238' b'216' b'8739954' b'39274' b'42198' b'12956'
 b'106868' b'53198' b'13060' b'39882' b'40594' b'44074' b'170' b'4147466'
 b'33606' b'1343564' b'108' b'258' b'39812' b'43342' b'9613730' b'13036'
 b'50366' b'2208732' b'39926' b'8106' b'7990616' b'2961522' b'38554'
 b'154' b'95314' b'38828' b'3215042' b'28440' b'42324' b'42136' b'39774'
 b'5156212' b'2484' b'4160930' b'12946' b'44338' b'3861806' b'13056'
 b'282' b'5787444' b'46616' b'42342' b'7918' b'49190' b'108728' b'146986'
 b'1159308' b'1228848' b'12958' b'2806864' b'43306' b'12600' b'88'
 b'40206' b'8180372' b'7545546' b'1299470' b'40856' b'149206' b'48784'
 b'44146' b'10862' b'6299724' b'42190' b'127076' b'3212' b'12908'
 b'2494898' b'6124522' b'862986' b'4244724' b'330' b'42760' b'9090622'
 b'127558' b'42294' b'228658' b'450648' b'7914' b'3063116' b'174'
 b'267292' b'10888' b'40798' b'651944' b'41174' b'2200558' b'10502' b'134'
 b'7894442' b'416692' b'2988' b'5944354' b'143050' b'1983758' b'45340'
 b'108686' b'278320' b'7142292' b'10852' b'308454' b'2065758' b'13040'
 b'7443562' b'325464' b'12902' b'171650' b'9314264' b'256' b'154962'
 b'702968' b'414812' b'296' b'1624616' b'42188' b'5218530' b'2305294'
 b'28824' b'292' b'39848' b'38544' b'91500' b'47354' b'4109950' b'44286'
 b'43122' b'410394' b'512060' b'307348' b'4200804' b'24680' b'6754426'
 b'13080' b'6062346' b'8927630' b'4539922' b'5337916' b'124264' b'48384'
 b'43850' b'5685516' b'408250' b'47512' b'78716' b'2850464' b'42302'
 b'13016' b'9160' b'1988138' b'86' b'299996' b'2479546' b'40456' b'654654'
 b'11300' b'41508' b'516892' b'174644' b'406980' b'156702' b'83996'
 b'13004' b'2200870' b'13062' b'8188696' b'527260' b'2867512' b'96718'
 b'6324' b'3961372' b'7396626' b'2262208' b'40656' b'119380' b'9127496'
 b'1277310' b'389828' b'5142878' b'2802666' b'6522868' b'157318' b'184562'
 b'105034' b'118' b'300694' b'6768022' b'12968' b'6260' b'541894'
 b'4999036' b'627212' b'22892' b'2543574' b'4678236' b'43712' b'2258044'
 b'6417010' b'1241626' b'1023626' b'4606' b'136310' b'41758' b'375586'
 b'45766' b'7724514' b'140' b'9204346' b'111212' b'1568220' b'41826'
 b'40580' b'83766' b'2484116' b'110' b'3851122' b'13438' b'528348'
 b'142590' b'905350' b'1078994' b'12990' b'1629674' b'363210' b'40854'
 b'44128' b'244' b'9620590' b'44560' b'2781138' b'114558' b'1719104'
 b'1634816' b'147256' b'43002' b'23198' b'44300' b'1241870' b'111866'
 b'1639798' b'6841092' b'9750390' b'12982' b'39876' b'6888458' b'154120'
 b'80410' b'276432' b'333510' b'151886' b'1177670' b'272816' b'416664'
 b'7759636' b'82' b'7751352' b'44588' b'42346' b'12828' b'440070' b'78'
 b'7868386' b'126' b'9064996' b'13466' b'8236906' b'6705892' b'190614'
 b'158660' b'686548' b'218' b'41240' b'265076' b'6408' b'230990' b'323358'
 b'755258' b'409042' b'182' b'420796' b'7590056' b'100924' b'13426'
 b'1966316' b'5423266' b'7752936' b'42354' b'443200' b'6114926' b'6414'
 b'39414' b'8793936' b'40418' b'690920' b'2028' b'13112' b'40090' b'21828'
 b'6610964' b'380988' b'384' b'391784' b'189070' b'9175152' b'45154'
 b'1194310' b'34908' b'78768' b'5574' b'31288' b'6824350' b'39834'
 b'44612' b'46598' b'2184766' b'578904' b'34720' b'387216' b'44680'
 b'39806' b'13436' b'6' b'1011566' b'1055992' b'335404' b'42488' b'8384'
 b'13552' b'3304044' b'12874' b'686832' b'314492' b'2560' b'274' b'40104'
 b'231508' b'49992' b'9572610' b'116376' b'322' b'2059202' b'42232'
 b'5449896' b'2283888' b'851600' b'47008' b'341932' b'8460192' b'1762012'
 b'8919972' b'308898' b'9253342' b'5058274' b'3069652' b'39396' b'41190'
 b'1701892' b'151338' b'158824' b'12962' b'2775016' b'445134' b'2258354'
 b'2508064' b'7029696' b'268680' b'9346750' b'4220844' b'8716' b'2144600'
 b'1202290' b'1933310' b'2829106' b'8934566' b'2063998' b'13378' b'45066'
 b'48980' b'593940' b'2652' b'40498' b'322136' b'44944' b'8028468'
 b'417552' b'7612456' b'7492566' b'3875072' b'3868872' b'2474510'
 b'495566' b'56202' b'41096' b'4511010' b'1087754' b'2217176' b'613368'
 b'42664' b'52100' b'5334926' b'3769458' b'80076' b'12894' b'9151844'
 b'301482' b'2739188' b'5142264' b'2428698' b'197590' b'480814' b'328'
 b'9490596' b'565362' b'48844' b'286' b'40846' b'342108' b'37638'
 b'335910' b'12918' b'105584' b'5408764' b'8509440' b'384156' b'42168'
 b'6743738' b'40658' b'5188844' b'722506' b'5536452' b'42262' b'45100'
 b'12914' b'180376' b'4215708' b'346562' b'4213864' b'150' b'611150'
 b'341564' b'73336' b'636190' b'228892' b'4050686' b'418046' b'4217848'
 b'9087796' b'124106' b'42326' b'43190' b'7602868' b'3222166' b'4559600'
 b'362374' b'8489566' b'6886520' b'3014622' b'7573488' b'5126982'
 b'8972988' b'13044' b'2602716' b'339454' b'1431556' b'10930' b'7938660'
 b'9645742' b'8317256' b'5325926' b'132' b'1008924' b'12906' b'37576'
 b'7804492' b'43856' b'5733092' b'5437546' b'42452' b'8527452' b'4372262'
 b'16086' b'54' b'42784' b'2906766' b'39954' b'12830' b'12910' b'1332120'
 b'5663142' b'1454538' b'8786792' b'1148858' b'874058' b'40430' b'42844'
 b'2803540' b'7274928' b'5006352' b'172330' b'964808' b'313734' b'53790'
 b'8295482' b'1350484' b'9120462' b'308' b'8532322' b'896422' b'10210472'
 b'8069214' b'40696' b'130144' b'105228' b'8423364' b'2727130' b'613082'
 b'4285350' b'151528' b'3489610' b'8717516' b'3977188' b'97138' b'7719530'
 b'270384' b'9480420' b'47672' b'1001862' b'43596' b'6369268' b'23892'
 b'299666' b'2711250' b'8716280' b'4095390' b'3690' b'266' b'52164'
 b'3404398' b'40326' b'2950662' b'576150' b'9173188' b'8180554' b'12952'
 b'580012' b'508024' b'43666' b'7966810' b'948804' b'663212' b'8499334'
 b'8061706' b'49286' b'3808' b'7881562' b'57268' b'46400' b'332402'
 b'8058340' b'1322894' b'7763546' b'6402514' b'722168' b'332334'
 b'6214036' b'24340' b'35094' b'5416586' b'2565688' b'166608' b'48176'
 b'105370' b'41844' b'46128' b'46' b'1284120' b'277600' b'176' b'5254528'
 b'441572' b'8771680' b'12924' b'7612414' b'42914' b'50822' b'43128'
 b'197922' b'42370' b'874580' b'269736' b'326' b'49668' b'1250582'
 b'6297860' b'279954' b'389710' b'1416766' b'40948' b'40758' b'50588'
 b'1813540' b'418124' b'1192120' b'28142' b'210552' b'8273936' b'810'
 b'39948' b'56366' b'7699444' b'45140' b'44094' b'2429002' b'4439448'
 b'4134756' b'7949542' b'797244' b'3400600' b'243662' b'195944' b'207132'
 b'1261946' b'61910' b'12880' b'1693480' b'232' b'52132' b'548628'
 b'45480' b'4200516' b'1919968' b'265176' b'850780' b'44042' b'234316'
 b'190326' b'13524' b'13134' b'765630' b'2551496' b'13628' b'731294'
 b'678836' b'155128' b'2977876' b'139190' b'33360' b'44480' b'2351218'
 b'9804124' b'1553824' b'375534' b'161530' b'309098' b'39836' b'418952'
 b'635116' b'136680' b'795854' b'2556888' b'296010' b'44456' b'1655624'
 b'466096' b'273262' b'753274' b'450522' b'336380' b'147980' b'904812'
 b'273136' b'3765514' b'100246' b'12920' b'2144262' b'38812' b'40072'
 b'1013382' b'64' b'9077888' b'9799128' b'830220' b'9131984' b'167654'
 b'2274594' b'4690242' b'24' b'13068' b'2466770' b'7556600' b'6824338'
 b'484984' b'12942' b'8158600' b'1024040' b'8002190' b'2921654' b'44388'
 b'153690' b'37552' b'48140' b'2173166' b'8354156' b'181422' b'1069306'
 b'187764' b'1170402' b'49442' b'657152' b'1768200' b'273122' b'5536498'
 b'44464' b'268' b'162248' b'2211854' b'510294' b'1557280' b'4389822'
 b'3106488' b'10379954' b'7334412' b'680442' b'5754078' b'6551786'
 b'645874' b'9072062' b'602' b'3064814' b'40064' b'40922' b'48792'
 b'353008' b'3943038' b'440860' b'41100' b'725178' b'3706522' b'49310'
 b'3223828' b'2348204' b'1834646' b'9404992' b'95252' b'40180' b'2978858'
 b'1639972' b'143928' b'1200390' b'376562' b'41092' b'86834' b'7659560'
 b'1866' b'1546508' b'9176102' b'3721646' b'264586' b'48064' b'706158'
 b'44154' b'1245808' b'151508' b'43456' b'43310' b'5382034' b'5689306'
 b'762102' b'3956196' b'42466' b'195266' b'590686' b'530258' b'43496'
 b'393802' b'45916' b'45384' b'2376' b'6566018' b'657838' b'147078'
 b'185670' b'1993624' b'44434' b'40478' b'28340' b'9088890' b'310838'
 b'9480124' b'53834' b'477574' b'45612' b'994596' b'431244' b'7086294'
 b'269346' b'543774' b'1686384' b'5566196' b'3605846' b'43264' b'276'
 b'8777612' b'359912' b'9485732' b'6769736' b'44744' b'115024' b'40082'
 b'5721248' b'755690' b'624326' b'233502' b'44288' b'180' b'164570'
 b'130534' b'1168952' b'294' b'870212' b'1214010' b'40714' b'119648'
 b'467442' b'42650' b'46158' b'44840' b'39944' b'265744' b'3684446'
 b'8645336' b'48252' b'272' b'9949618' b'45432' b'46476' b'37580' b'162'
 b'7715552' b'44130' b'2416768' b'325264' b'188720' b'46988' b'131396'
 b'231106' b'2326048' b'152022' b'45736' b'9901020' b'400144' b'732662'
 b'751438' b'332102' b'366048' b'844102' b'121590' b'1165844' b'42344'
 b'40840' b'9635830' b'22' b'7930874' b'125426' b'254' b'42922' b'462954'
 b'1091510' b'74930' b'29434' b'40830' b'5063234' b'53192' b'12970'
 b'851232' b'640460' b'196' b'265720' b'39190' b'1148866' b'9224874'
 b'1225456' b'146580' b'9326534' b'999490' b'115960' b'823450' b'5091926'
 b'46914' b'9319188' b'142368' b'7006352' b'7434996' b'1149362' b'1882452'
 b'460948' b'6542998' b'6194036' b'596054' b'1422648' b'387560' b'304862'
 b'28346' b'33670' b'374700' b'3570442' b'1745166' b'5033204' b'42330'
 b'2166702' b'167458' b'13400' b'731450' b'2913876' b'202' b'13070'
 b'44274' b'9489092' b'6283362' b'109570' b'42172' b'9493760' b'1667226'
 b'53402' b'43482' b'744608' b'5862740' b'156770' b'3864516' b'159106'
 b'192' b'38314' b'34786' b'74894' b'3603276' b'4886474' b'588436'
 b'57838' b'773094' b'967110' b'312356' b'9676594' b'2849856' b'9172576'
 b'6896848' b'41276' b'353386' b'7141192' b'495436' b'9391646' b'753796'
 b'9986782' b'126006' b'4331106' b'6069720' b'3583172' b'46776' b'42736'
 b'224640' b'922256' b'42722' b'8538678' b'12966' b'453186' b'2790012'
 b'40938' b'3044676' b'2008128' b'5634786' b'236918' b'3626084' b'8359702'
 b'2809316' b'3989940' b'1079580' b'10233910' b'39470' b'43792' b'7808958'
 b'2964666' b'245982' b'4296148' b'1395516' b'523170' b'90' b'40968']
Feature: top_1_7_day_fresh_product
Tensor: [b'3860' b'1264' b'44' b'1260' b'NA' b'156' b'1448' b'176' b'13416'
 b'8764' b'811012' b'100' b'51224' b'438616' b'1164' b'48' b'3500'
 b'41608' b'1532' b'2124' b'57776' b'7732' b'1192' b'6716' b'811020'
 b'79080' b'74448' b'4224' b'1180' b'555620' b'41428' b'148984' b'6732'
 b'5996' b'4452' b'2764' b'6936' b'66816' b'188' b'72512' b'67576'
 b'110564' b'3160' b'5752' b'52' b'420336' b'11792' b'2116' b'3048'
 b'1376' b'8328' b'2312' b'949864' b'2500' b'2564' b'3176' b'10884'
 b'87484' b'732924' b'49792' b'2120' b'4744' b'1340' b'2320' b'49776'
 b'90068' b'49384' b'64836' b'66104' b'2692' b'1504' b'3080' b'555576'
 b'264088' b'9272' b'41432' b'1372' b'811076' b'2720' b'77312' b'3188'
 b'556188' b'41768' b'64128' b'245408' b'4416' b'7324' b'6000' b'6724'
 b'121676' b'3376' b'1444' b'61244' b'68100' b'71800' b'9264' b'3356'
 b'2316' b'76108' b'49780' b'88576' b'1172' b'123724' b'93652' b'71364'
 b'32824' b'65464' b'3184' b'5552' b'67956' b'7128' b'81188' b'52112'
 b'52140' b'2160' b'3504' b'57700' b'8248' b'458128' b'67940' b'151976'
 b'49600' b'188700' b'81764' b'88740' b'429736' b'48012' b'4348' b'9852'
 b'5712' b'5092' b'52084' b'83576' b'65568' b'41452' b'8072' b'73000'
 b'914204' b'6124' b'2596']
Feature: top_2_7_day_fresh_product
Tensor: [b'44' b'8520' b'176' b'2120' b'NA' b'188' b'3356' b'1164' b'1260'
 b'811428' b'2764' b'13416' b'1444' b'2692' b'1264' b'1376' b'41452'
 b'133116' b'96956' b'2116' b'156' b'327444' b'4744' b'48012' b'14468'
 b'52' b'1192' b'2564' b'66308' b'1372' b'57704' b'811772' b'3500'
 b'462508' b'2124' b'8764' b'41432' b'52108' b'555748' b'148984' b'1176'
 b'2312' b'9856' b'7324' b'49808' b'4224' b'4416' b'9264' b'100' b'3160'
 b'110564' b'88740' b'1172' b'452212' b'4912' b'6640' b'3080' b'59128'
 b'78348' b'9852' b'259324' b'6128' b'5692' b'93652' b'49784' b'70176'
 b'48' b'5752' b'5092' b'5452' b'732952' b'811076' b'3316' b'41120'
 b'49792' b'64128' b'3184' b'3732' b'76108' b'49616' b'10920' b'1504'
 b'811012' b'1532' b'49788' b'6724' b'1180' b'3504' b'41428' b'2316'
 b'74796' b'49384' b'41756' b'71800' b'452304' b'811120' b'215600' b'9568'
 b'3176' b'235472' b'144528' b'67052' b'65964' b'5744' b'458128' b'5996'
 b'811192' b'16296' b'121676' b'10000' b'4348' b'66924' b'65564' b'62604'
 b'90024' b'2720' b'64132' b'4828' b'12872' b'77312' b'6732' b'3020'
 b'1448' b'61244' b'3048' b'6936' b'64836' b'811024' b'3376' b'7732'
 b'7872' b'2320' b'188620' b'74448' b'67116' b'41380' b'66816' b'65144'
 b'67956' b'90068' b'54124' b'78388' b'4840' b'54148' b'7128' b'446792'
 b'717000' b'944936' b'49780' b'16336' b'49800' b'37132' b'452220' b'2560'
 b'60580' b'452240' b'839892' b'452244' b'41540' b'151976' b'41352'
 b'41324' b'112436' b'67576' b'70448' b'214460' b'11792' b'41216' b'2204'
 b'54160']
Feature: top_3_7_day_fresh_product
Tensor: [b'156' b'176' b'1260' b'78400' b'188' b'NA' b'1164' b'4452' b'74448'
 b'1264' b'2116' b'811020' b'327444' b'41452' b'2764' b'33652' b'4744'
 b'6936' b'1372' b'106660' b'62604' b'2316' b'3356' b'3160' b'148984'
 b'66572' b'93652' b'3048' b'2500' b'67116' b'100' b'77312' b'2312'
 b'2120' b'70412' b'1444' b'44' b'1532' b'49808' b'1176' b'1172' b'52'
 b'48' b'555784' b'1192' b'11152' b'49816' b'7324' b'77808' b'11596'
 b'1448' b'5048' b'1376' b'2692' b'2124' b'41204' b'74796' b'14468'
 b'67956' b'10652' b'59128' b'613360' b'41768' b'3860' b'41464' b'4348'
 b'75904' b'41776' b'3188' b'8248' b'49464' b'9856' b'49800' b'5752'
 b'66308' b'70940' b'54124' b'811964' b'86792' b'4828' b'71800' b'1504'
 b'555576' b'7872' b'4416' b'3080' b'90068' b'76108' b'49456' b'64132'
 b'10920' b'8764' b'37120' b'65568' b'452324' b'5744' b'3176' b'86852'
 b'48012' b'6640' b'41380' b'64128' b'110564' b'54160' b'2720' b'64572'
 b'9568' b'2320' b'3184' b'41604' b'96956' b'3364' b'41428' b'452220'
 b'67268' b'3500' b'452352' b'9272' b'2564' b'67576' b'120284' b'70448'
 b'2160' b'6124' b'8168' b'77516' b'6724' b'41312' b'605148' b'188700'
 b'3504' b'99268' b'452244' b'6128' b'1180' b'5692' b'52188' b'959780'
 b'90024' b'185620' b'71284' b'555588' b'103652' b'2596' b'438616'
 b'242736' b'458128' b'336724' b'13416' b'37136' b'77544' b'4836' b'85268'
 b'65564' b'4224' b'51224' b'10000' b'564916' b'41120' b'65464']
Feature: top_4_7_day_fresh_product
Tensor: [b'1260' b'2160' b'1264' b'79028' b'NA' b'4912' b'2124' b'1164' b'4828'
 b'2316' b'156' b'32824' b'9232' b'2692' b'3188' b'93652' b'100' b'2204'
 b'64836' b'4224' b'77684' b'176' b'9264' b'3176' b'14652' b'1376' b'2120'
 b'3160' b'8248' b'1532' b'1448' b'3500' b'90068' b'6640' b'9856' b'2564'
 b'1176' b'188' b'8520' b'2312' b'54124' b'1504' b'74448' b'2764' b'44'
 b'52' b'3356' b'4744' b'1172' b'52096' b'110564' b'5048' b'438616'
 b'1180' b'185620' b'77312' b'62604' b'361736' b'4452' b'1444' b'2116'
 b'1192' b'5744' b'3504' b'11260' b'10920' b'65884' b'48' b'1340' b'6732'
 b'94608' b'41428' b'52112' b'41352' b'13416' b'452352' b'6724' b'7920'
 b'3184' b'41432' b'41324' b'2500' b'70372' b'4416' b'14468' b'11152'
 b'3732' b'1372' b'65144' b'8328' b'49612' b'235772' b'7324' b'61244'
 b'77516' b'66924' b'67940' b'33736' b'2720' b'78400' b'7732' b'98700'
 b'41388' b'1156' b'452304' b'54148' b'259324' b'11792' b'49640' b'7480'
 b'67956' b'787368' b'99560' b'65568' b'52140' b'108772' b'780612'
 b'264088' b'6936' b'103652' b'49800' b'3080' b'452244' b'142956' b'76108'
 b'5452' b'3168' b'988024' b'10000' b'71800' b'41312' b'88740' b'811008'
 b'235472' b'65132' b'613360' b'34476' b'41756' b'67052' b'5568' b'74796'
 b'188700' b'148984' b'214460' b'5724' b'78288' b'816568' b'144528'
 b'59128' b'112436']
Feature: top_5_7_day_fresh_product
Tensor: [b'176' b'2320' b'2316' b'NA' b'9856' b'1372' b'66924' b'3080' b'44'
 b'5552' b'2312' b'1260' b'452300' b'2564' b'3732' b'4744' b'110564'
 b'1448' b'2764' b'41428' b'52' b'4452' b'148984' b'3356' b'8764' b'6640'
 b'1264' b'156' b'4416' b'48' b'8520' b'2116' b'2692' b'3860' b'5996'
 b'7128' b'11152' b'74448' b'10432' b'3160' b'61244' b'3188' b'3376'
 b'188620' b'9264' b'77312' b'2124' b'1164' b'1192' b'555576' b'1532'
 b'5568' b'839892' b'5692' b'2120' b'4912' b'4828' b'11792' b'1176'
 b'90024' b'151976' b'77000' b'188' b'1444' b'14468' b'74780' b'41204'
 b'7324' b'75564' b'59128' b'49808' b'188700' b'52192' b'3504' b'811008'
 b'77684' b'173104' b'5092' b'5744' b'90660' b'67956' b'8248' b'65564'
 b'140080' b'81896' b'52140' b'822276' b'777184' b'4224' b'62604' b'7732'
 b'76108' b'93652' b'64836' b'92396' b'103652' b'2324' b'52112' b'66520'
 b'79028' b'74796' b'41120' b'70376' b'66820' b'259324' b'3364' b'1504'
 b'2720' b'10304' b'41452' b'41756' b'41432' b'41604' b'64132' b'3500'
 b'787456' b'64572' b'811108' b'65144' b'12884' b'9844' b'71800' b'787256'
 b'57704' b'7872' b'78400' b'1172' b'811024' b'49780' b'214460' b'6716'
 b'2596' b'1376' b'3048' b'3184' b'41464' b'57692' b'90068' b'85792'
 b'361736' b'811428' b'100' b'41716' b'66104' b'37120' b'71260' b'33652'
 b'6936' b'51224' b'215984' b'102644' b'235472']
Feature: top_1_15_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'176' b'156' b'NA' b'66924' b'13416' b'8764'
 b'811020' b'100' b'51224' b'438616' b'6936' b'1164' b'2312' b'458128'
 b'52' b'1340' b'2116' b'2124' b'77312' b'7128' b'3500' b'2120' b'2316'
 b'4744' b'4224' b'3376' b'1532' b'1180' b'555620' b'235772' b'4416'
 b'5048' b'2764' b'188' b'67576' b'110564' b'1444' b'11792' b'3356'
 b'59128' b'1376' b'11260' b'10920' b'949864' b'1192' b'90068' b'5092'
 b'10884' b'87484' b'732924' b'49792' b'3316' b'74448' b'93652' b'41452'
 b'103652' b'3160' b'48' b'67116' b'76108' b'49384' b'1172' b'66104'
 b'811012' b'3080' b'3504' b'41428' b'3732' b'49480' b'452244' b'555576'
 b'264088' b'41756' b'1504' b'2376' b'811076' b'2720' b'1448' b'37120'
 b'3188' b'556188' b'64656' b'41768' b'2692' b'452304' b'5744' b'7324'
 b'16296' b'62604' b'2564' b'4348' b'148984' b'8328' b'9264' b'141148'
 b'49780' b'88576' b'4912' b'7732' b'1372' b'6716' b'123724' b'9856'
 b'41120' b'3860' b'54124' b'5552' b'67956' b'52112' b'2160' b'10648'
 b'57700' b'2500' b'2320' b'6640' b'49800' b'1176' b'57708' b'67940'
 b'151976' b'8168' b'49600' b'188700' b'81764' b'119944' b'922492'
 b'48012' b'78400' b'5712' b'52084' b'83576' b'361736' b'4452' b'41324'
 b'65568' b'10656' b'6732' b'914204' b'6124' b'2596']
Feature: top_2_15_day_fresh_product
Tensor: [b'44' b'8520' b'176' b'1164' b'NA' b'188' b'1264' b'41428' b'100' b'1260'
 b'811428' b'2764' b'2316' b'1444' b'2692' b'2116' b'41452' b'133116'
 b'3080' b'9264' b'2312' b'156' b'4744' b'14468' b'110564' b'2564'
 b'57776' b'10884' b'7732' b'1372' b'1448' b'3500' b'88576' b'8764'
 b'79080' b'1532' b'1376' b'11152' b'452352' b'555748' b'10816' b'41608'
 b'1176' b'1192' b'7324' b'12064' b'4224' b'77312' b'2124' b'4452'
 b'41120' b'41772' b'3160' b'88740' b'2596' b'48' b'2320' b'1172' b'74448'
 b'420336' b'6640' b'9856' b'52' b'67956' b'6724' b'77000' b'246112'
 b'2120' b'93652' b'6936' b'3184' b'732952' b'811076' b'188620' b'945464'
 b'49776' b'64128' b'41768' b'3732' b'49616' b'54124' b'1504' b'65564'
 b'452252' b'48012' b'70372' b'1180' b'66924' b'41540' b'9272' b'8328'
 b'49384' b'71800' b'76108' b'71260' b'3356' b'5712' b'67052' b'65964'
 b'452244' b'811192' b'438616' b'6000' b'85104' b'41380' b'787368' b'3188'
 b'235472' b'10000' b'121676' b'87344' b'66820' b'10920' b'62604' b'61244'
 b'452304' b'12872' b'2720' b'64836' b'7480' b'49800' b'3376' b'4416'
 b'2160' b'6124' b'71364' b'4912' b'65568' b'787256' b'235772' b'11596'
 b'11752' b'3176' b'581832' b'90068' b'81188' b'3504' b'52192' b'2500'
 b'1340' b'2376' b'59128' b'7128' b'57704' b'446792' b'717000' b'944936'
 b'8248' b'41716' b'458128' b'60580' b'839892' b'79028' b'4348' b'64132'
 b'5744' b'151976' b'41352' b'2324' b'67576' b'16296' b'214460' b'70316'
 b'87976' b'41216' b'2204' b'34484' b'54160']
Feature: top_3_15_day_fresh_product
Tensor: [b'156' b'176' b'1260' b'NA' b'1164' b'1448' b'44' b'7732' b'2116'
 b'811012' b'327444' b'41452' b'2764' b'33652' b'452300' b'1264' b'1376'
 b'48' b'2312' b'2692' b'3188' b'8764' b'41120' b'90068' b'452352' b'2120'
 b'3160' b'148984' b'1532' b'41428' b'93652' b'188' b'1192' b'52' b'100'
 b'67116' b'3364' b'6716' b'3048' b'945464' b'1372' b'2124' b'49808'
 b'74448' b'613360' b'76108' b'1172' b'556188' b'555784' b'88576' b'66308'
 b'9856' b'11152' b'62604' b'6936' b'41716' b'41324' b'65132' b'1444'
 b'4828' b'77312' b'3860' b'452212' b'4912' b'4416' b'5752' b'86520'
 b'2316' b'59128' b'78348' b'8328' b'1180' b'3356' b'556808' b'3020'
 b'37128' b'6724' b'2564' b'5712' b'4348' b'67956' b'922528' b'8520'
 b'49792' b'173104' b'9272' b'64836' b'2500' b'9852' b'1504' b'555576'
 b'71356' b'74796' b'3080' b'65144' b'48012' b'49456' b'3504' b'64132'
 b'57700' b'78400' b'1176' b'9568' b'3176' b'5744' b'67576' b'245408'
 b'458128' b'14468' b'57708' b'86852' b'110564' b'73008' b'2720' b'41604'
 b'96956' b'54148' b'48780' b'810996' b'120284' b'61244' b'52188' b'41768'
 b'37168' b'41380' b'32824' b'3184' b'99268' b'49800' b'452244' b'179940'
 b'54124' b'5692' b'4452' b'4840' b'52140' b'2596' b'41156' b'73264'
 b'90024' b'41204' b'87344' b'71284' b'555588' b'7324' b'37132' b'48772'
 b'88740' b'3732' b'336724' b'3500' b'37136' b'77544' b'188700' b'121676'
 b'4836' b'85268' b'66816' b'5552' b'2376' b'90852' b'8072' b'51224'
 b'11352' b'5724' b'7128' b'57704' b'564916' b'37124']
Feature: top_4_15_day_fresh_product
Tensor: [b'3860' b'2160' b'1264' b'1448' b'1260' b'NA' b'4452' b'74448' b'1164'
 b'811944' b'13416' b'452324' b'1444' b'3500' b'41756' b'41608' b'452352'
 b'93652' b'176' b'2124' b'11152' b'8764' b'44' b'4416' b'90024' b'3048'
 b'2500' b'1372' b'2764' b'3176' b'2120' b'2116' b'3160' b'90068'
 b'811772' b'1192' b'156' b'462508' b'1532' b'3184' b'110564' b'188' b'52'
 b'14468' b'112436' b'2312' b'52096' b'3504' b'76108' b'66816' b'65964'
 b'78348' b'438616' b'5048' b'2564' b'52188' b'3188' b'1376' b'2692'
 b'2316' b'4224' b'41120' b'79028' b'1176' b'6936' b'1172' b'5744'
 b'16344' b'64132' b'3080' b'9272' b'41768' b'6128' b'49784' b'100' b'48'
 b'5752' b'62604' b'41428' b'1340' b'246112' b'49800' b'839892' b'66308'
 b'2204' b'264088' b'10920' b'41324' b'37132' b'811964' b'49788' b'41604'
 b'71800' b'1504' b'7872' b'3732' b'7732' b'78400' b'49612' b'4744'
 b'7324' b'54124' b'6640' b'452304' b'811120' b'2320' b'41216' b'77516'
 b'3356' b'4912' b'54148' b'555576' b'48012' b'7128' b'67116' b'74796'
 b'4828' b'79064' b'64572' b'452244' b'9568' b'8328' b'452220' b'61244'
 b'67268' b'49596' b'811024' b'787368' b'64764' b'57692' b'65564' b'8168'
 b'605148' b'65144' b'103652' b'121676' b'11260' b'54160' b'76348' b'1180'
 b'10000' b'64128' b'66924' b'811952' b'959780' b'2720' b'70136' b'16336'
 b'811008' b'16280' b'235772' b'241064' b'49492' b'2560' b'452240'
 b'337124' b'67956' b'429736' b'5568' b'9264' b'214460' b'922528'
 b'151976' b'816568' b'144528' b'4200']
Feature: top_5_15_day_fresh_product
Tensor: [b'3500' b'2320' b'2316' b'2120' b'1264' b'NA' b'1372' b'4912' b'64132'
 b'2312' b'14468' b'176' b'839892' b'2124' b'2116' b'3732' b'41452'
 b'54148' b'62604' b'188' b'3356' b'327444' b'48012' b'9264' b'3176'
 b'10816' b'1192' b'3160' b'4828' b'1164' b'156' b'66308' b'52' b'3860'
 b'452244' b'100' b'1260' b'2564' b'1176' b'41432' b'1180' b'1532' b'2376'
 b'54124' b'48' b'2692' b'3184' b'44' b'7324' b'77808' b'10920' b'85268'
 b'361736' b'1172' b'41120' b'1444' b'1448' b'4744' b'3188' b'3080'
 b'6936' b'88740' b'151976' b'2764' b'3504' b'3048' b'65884' b'75756'
 b'76108' b'74448' b'103652' b'2500' b'1340' b'59128' b'49808' b'41464'
 b'71052' b'52084' b'1376' b'8248' b'452352' b'7920' b'16312' b'67116'
 b'70940' b'86792' b'188700' b'52140' b'188620' b'556808' b'235772'
 b'7732' b'5996' b'61244' b'47984' b'92396' b'2560' b'3364' b'120284'
 b'5552' b'2324' b'79028' b'52112' b'33736' b'2720' b'71260' b'74796'
 b'13416' b'57776' b'41604' b'66820' b'93652' b'11152' b'10304' b'4416'
 b'452304' b'259324' b'11792' b'787456' b'70448' b'64128' b'77516' b'8764'
 b'780612' b'52192' b'110564' b'57704' b'811192' b'41428' b'78400'
 b'49796' b'67044' b'4224' b'142956' b'3168' b'41716' b'64536' b'5692'
 b'185620' b'90068' b'235472' b'78132' b'1504' b'438616' b'5048' b'77312'
 b'64656' b'67956' b'840108' b'7128' b'41776' b'6724' b'65464' b'68224']
Feature: top_1_60_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'176' b'8536' b'66924' b'184' b'8764' b'811020'
 b'100' b'1164' b'438616' b'2116' b'2692' b'41608' b'49600' b'2312' b'156'
 b'NA' b'1340' b'52108' b'5716' b'6640' b'4416' b'77312' b'9264' b'7128'
 b'3500' b'1376' b'76108' b'4224' b'1172' b'1180' b'73260' b'98784'
 b'1192' b'9856' b'7324' b'3160' b'12064' b'5048' b'452244' b'613076'
 b'70376' b'48' b'188' b'452212' b'110564' b'3356' b'2124' b'2120' b'52'
 b'1444' b'41464' b'59128' b'77000' b'5552' b'246112' b'556808' b'65884'
 b'74448' b'2500' b'1532' b'57700' b'2564' b'41432' b'732952' b'49792'
 b'3316' b'41452' b'67116' b'49788' b'3080' b'48012' b'6724' b'2764'
 b'3504' b'41428' b'49480' b'2560' b'74796' b'2316' b'41756' b'1504'
 b'6832' b'811076' b'2720' b'1176' b'556188' b'14672' b'41768' b'65964'
 b'452304' b'16296' b'62604' b'4348' b'41324' b'41120' b'34484' b'71260'
 b'5744' b'96956' b'61244' b'3048' b'49780' b'461668' b'103652' b'52188'
 b'1448' b'65568' b'37128' b'49596' b'64132' b'67956' b'811024' b'6716'
 b'65144' b'1372' b'3184' b'71800' b'9272' b'529128' b'54124' b'452368'
 b'811008' b'49808' b'8168' b'51224' b'151976' b'60580' b'2596' b'88740'
 b'78400' b'2160' b'839892' b'83576' b'5712' b'52084' b'361736' b'66104'
 b'10920' b'90068' b'5724' b'914204' b'6936' b'144528' b'4200']
Feature: top_2_60_day_fresh_product
Tensor: [b'44' b'176' b'1264' b'1260' b'NA' b'156' b'2560' b'11596' b'100' b'1164'
 b'811428' b'2316' b'2596' b'41452' b'133116' b'65884' b'65464' b'2116'
 b'2124' b'2764' b'4744' b'64572' b'93652' b'8244' b'88740' b'3500'
 b'2564' b'179940' b'7732' b'74448' b'6716' b'3048' b'3176' b'2120'
 b'8764' b'9856' b'4416' b'1532' b'3376' b'2312' b'1448' b'14672' b'65568'
 b'5048' b'54148' b'70940' b'49808' b'4224' b'77312' b'7324' b'5752'
 b'41120' b'564896' b'1172' b'67576' b'142956' b'3160' b'6936' b'811944'
 b'3504' b'57692' b'188' b'65128' b'8328' b'2320' b'1176' b'52' b'85104'
 b'4828' b'52140' b'5712' b'10884' b'87484' b'811076' b'67940' b'86520'
 b'246112' b'452304' b'1192' b'839892' b'7128' b'48' b'148984' b'1372'
 b'1504' b'41324' b'2720' b'811012' b'49788' b'110564' b'52188' b'66924'
 b'3188' b'49388' b'452244' b'52156' b'9272' b'121676' b'41756' b'2500'
 b'41428' b'52096' b'82408' b'3080' b'37120' b'66820' b'67052' b'438616'
 b'245408' b'2692' b'86852' b'4348' b'4452' b'1444' b'67116' b'3184'
 b'65564' b'64128' b'3364' b'9264' b'10920' b'26792' b'82868' b'452324'
 b'90068' b'49596' b'66308' b'52108' b'7480' b'810996' b'88576' b'4912'
 b'77652' b'65144' b'1180' b'3356' b'81676' b'581832' b'51224' b'2324'
 b'81188' b'52192' b'5996' b'2376' b'184' b'6724' b'2204' b'446792'
 b'76348' b'107676' b'49780' b'49800' b'103652' b'8168' b'64764' b'48012'
 b'41432' b'79028' b'5552' b'49604' b'452300' b'5092' b'82940' b'811000'
 b'62604' b'3732' b'76108' b'57776' b'66104' b'6124']
Feature: top_3_60_day_fresh_product
Tensor: [b'156' b'2312' b'1260' b'44' b'100' b'NA' b'176' b'5744' b'4348' b'1164'
 b'811012' b'3160' b'41452' b'1376' b'33652' b'52140' b'2116' b'1264'
 b'77312' b'7872' b'66308' b'458128' b'1172' b'2316' b'74448' b'3364'
 b'14468' b'141704' b'188' b'1372' b'2764' b'4416' b'246112' b'12064'
 b'1532' b'88576' b'4224' b'811020' b'48784' b'4828' b'49808' b'1180'
 b'9264' b'52' b'452352' b'2564' b'73264' b'2500' b'148984' b'3504'
 b'1192' b'6124' b'3188' b'6936' b'41716' b'2124' b'839892' b'564912'
 b'41380' b'7128' b'949664' b'62604' b'90676' b'556808' b'11908' b'6724'
 b'11260' b'77000' b'48' b'7324' b'8764' b'2320' b'77808' b'2120' b'67956'
 b'1444' b'71052' b'6716' b'8240' b'5048' b'188620' b'71800' b'41428'
 b'41540' b'3080' b'1448' b'847168' b'64128' b'41768' b'54124' b'1408'
 b'2692' b'452252' b'70372' b'71356' b'49472' b'90068' b'70424' b'264088'
 b'8520' b'65144' b'3184' b'2560' b'2376' b'11596' b'6640' b'4744' b'3168'
 b'81188' b'73008' b'811192' b'67576' b'6000' b'74796' b'85104' b'57776'
 b'787368' b'452304' b'121676' b'64132' b'87344' b'2720' b'88740' b'3356'
 b'41604' b'9272' b'8328' b'67940' b'54148' b'3732' b'49596' b'811024'
 b'555576' b'1504' b'452220' b'65568' b'787256' b'1176' b'52192' b'110564'
 b'9856' b'57692' b'49800' b'65548' b'59128' b'41756' b'49488' b'5752'
 b'3048' b'2596' b'76108' b'5552' b'41732' b'65464' b'93652' b'66924'
 b'904620' b'57700' b'7732' b'811772' b'452240' b'65296' b'48772' b'81764'
 b'151976' b'64764' b'3176' b'49792' b'33644' b'83576' b'2160' b'41464'
 b'605148' b'6732' b'41216' b'34484' b'54160']
Feature: top_4_60_day_fresh_product
Tensor: [b'176' b'8520' b'1264' b'NA' b'1260' b'2692' b'1372' b'13416' b'188'
 b'2116' b'811944' b'1164' b'41768' b'1444' b'3080' b'156' b'1448' b'48'
 b'52' b'5048' b'77312' b'100' b'2120' b'44' b'74448' b'4452' b'2764'
 b'2312' b'2500' b'3160' b'581832' b'10884' b'1532' b'3364' b'452240'
 b'41428' b'462508' b'1176' b'438616' b'62604' b'14468' b'2316' b'3176'
 b'246112' b'11152' b'2124' b'9264' b'1192' b'3504' b'110564' b'41324'
 b'2564' b'5744' b'179940' b'41540' b'6936' b'1376' b'67956' b'65884'
 b'1172' b'88740' b'41216' b'79064' b'76108' b'59128' b'37132' b'3184'
 b'10432' b'9272' b'732924' b'4744' b'71264' b'452304' b'49776' b'7128'
 b'839900' b'184' b'8764' b'78400' b'66104' b'41432' b'6320' b'48636'
 b'4416' b'7872' b'8328' b'49600' b'49816' b'3732' b'79636' b'77544'
 b'79028' b'41196' b'41120' b'66308' b'9844' b'4828' b'41604' b'452212'
 b'7732' b'3860' b'185620' b'70376' b'74796' b'90068' b'839892' b'3500'
 b'65548' b'93652' b'3356' b'3188' b'6732' b'86792' b'452220' b'1180'
 b'11792' b'9568' b'3168' b'52140' b'845268' b'41716' b'61244' b'11752'
 b'11908' b'6124' b'8168' b'79080' b'5552' b'41172' b'52156' b'613360'
 b'108772' b'564916' b'64772' b'5692' b'86852' b'52112' b'2560' b'103652'
 b'64128' b'121676' b'5996' b'2720' b'605420' b'2596' b'49784' b'3048'
 b'555576' b'10648' b'87344' b'11596' b'33708' b'810996' b'5860' b'57708'
 b'88576' b'49388' b'188700' b'119944' b'2320' b'67116' b'51224' b'6832'
 b'811076' b'151976' b'214460' b'97240' b'84120' b'92396' b'816568'
 b'78388' b'1504' b'37124' b'8244']
Feature: top_5_60_day_fresh_product
Tensor: [b'1264' b'156' b'2316' b'1164' b'44' b'NA' b'188' b'2120' b'64572'
 b'1172' b'1260' b'78388' b'1448' b'65144' b'6936' b'2312' b'140080'
 b'2764' b'176' b'64836' b'4416' b'13416' b'3048' b'3500' b'7324' b'2692'
 b'5752' b'2124' b'3364' b'100' b'6640' b'2116' b'51224' b'90068' b'9856'
 b'48' b'41812' b'1192' b'41432' b'74448' b'452244' b'52' b'1532'
 b'452300' b'5552' b'1176' b'52096' b'62604' b'438616' b'4452' b'66816'
 b'41732' b'3188' b'2596' b'41120' b'3160' b'64128' b'1376' b'1444'
 b'811052' b'11792' b'3356' b'245720' b'71264' b'1180' b'70372' b'2564'
 b'76108' b'70176' b'77544' b'811000' b'41756' b'41428' b'945464'
 b'787256' b'1372' b'581832' b'5048' b'3080' b'3184' b'5996' b'3504'
 b'3732' b'264088' b'452324' b'49384' b'9272' b'41708' b'9852' b'86792'
 b'41604' b'4828' b'5716' b'14468' b'41540' b'11260' b'59128' b'67940'
 b'88740' b'8764' b'3860' b'93652' b'41716' b'103652' b'2320' b'839900'
 b'64132' b'4348' b'65084' b'5744' b'52140' b'6124' b'2720' b'78400'
 b'41380' b'787456' b'67116' b'206252' b'3176' b'8328' b'452220' b'452304'
 b'66308' b'2308' b'556188' b'65296' b'603460' b'811968' b'65384' b'57700'
 b'603440' b'65564' b'8248' b'64968' b'41768' b'71800' b'65108' b'7732'
 b'605148' b'71260' b'77312' b'4912' b'246112' b'16344' b'9264' b'811428'
 b'79028' b'67956' b'76348' b'5692' b'7872' b'49804' b'845268' b'2500'
 b'2160' b'839892' b'37172' b'4744' b'110564' b'41724' b'109768' b'185620'
 b'12356' b'10920' b'1340' b'377356' b'86520' b'458128' b'54124' b'49600'
 b'12872' b'33652' b'41216' b'4224' b'78432' b'86852' b'607836' b'65568'
 b'70304' b'277204' b'5712' b'74796' b'6724' b'77516' b'2560']
Feature: top_1_90_day_fresh_product
Tensor: [b'1260' b'1264' b'44' b'66924' b'176' b'77000' b'11596' b'811020' b'100'
 b'1164' b'438616' b'41452' b'65884' b'49600' b'2312' b'2116' b'1376'
 b'NA' b'8764' b'1340' b'2500' b'5716' b'3500' b'6640' b'4416' b'77312'
 b'12064' b'9264' b'74448' b'7128' b'156' b'52' b'76108' b'4224' b'1172'
 b'1180' b'14672' b'98784' b'9856' b'7324' b'70940' b'452244' b'613076'
 b'564896' b'2316' b'48788' b'2124' b'102640' b'110564' b'3356' b'2120'
 b'2764' b'1444' b'59128' b'5552' b'246112' b'1448' b'3160' b'1532'
 b'57704' b'2564' b'41432' b'732952' b'49792' b'1192' b'3316' b'839892'
 b'67116' b'48012' b'6724' b'2204' b'3504' b'41428' b'49480' b'2560'
 b'41756' b'1372' b'1504' b'6832' b'2720' b'1176' b'556188' b'48'
 b'452304' b'16296' b'4452' b'62604' b'4348' b'41324' b'41120' b'188'
 b'34484' b'88740' b'96956' b'61244' b'11792' b'49780' b'5744' b'461668'
 b'3184' b'103652' b'52188' b'77652' b'49596' b'8328' b'67956' b'811428'
 b'6716' b'3080' b'65144' b'2376' b'57700' b'71800' b'9272' b'529128'
 b'54124' b'811008' b'86520' b'52140' b'8168' b'88576' b'2596' b'78400'
 b'41768' b'2160' b'52084' b'83576' b'361736' b'66104' b'10920' b'90068'
 b'914204' b'54160' b'6936' b'144528' b'4200']
Feature: top_2_90_day_fresh_product
Tensor: [b'44' b'176' b'1260' b'2204' b'156' b'1264' b'3364' b'8764' b'13416'
 b'1164' b'811012' b'2316' b'2596' b'2692' b'140080' b'65464' b'NA'
 b'2764' b'4744' b'64572' b'93652' b'3048' b'52108' b'8244' b'2564'
 b'108772' b'2124' b'581832' b'7732' b'3500' b'1192' b'74448' b'4224'
 b'4828' b'2120' b'9856' b'4416' b'1532' b'1448' b'2116' b'73264' b'3080'
 b'49808' b'2312' b'839892' b'12872' b'48784' b'564912' b'100' b'41432'
 b'188' b'67576' b'142956' b'3160' b'6936' b'4348' b'86520' b'57692'
 b'59128' b'556808' b'78348' b'3504' b'11260' b'52' b'85104' b'52140'
 b'6732' b'5712' b'10884' b'1172' b'71052' b'732924' b'811076' b'452352'
 b'71800' b'780612' b'1376' b'77312' b'1372' b'148984' b'41324' b'37132'
 b'246112' b'52188' b'3188' b'49388' b'74796' b'52156' b'9272' b'8328'
 b'121676' b'1180' b'2500' b'41428' b'2320' b'82408' b'37120' b'66820'
 b'110564' b'14672' b'185620' b'67052' b'5448' b'70412' b'86852' b'9264'
 b'787368' b'452304' b'66924' b'65564' b'41120' b'64128' b'11792' b'1504'
 b'88740' b'5744' b'452212' b'82868' b'3184' b'452324' b'90068' b'14468'
 b'49596' b'48' b'48776' b'1444' b'98700' b'65144' b'6124' b'1176'
 b'922492' b'65568' b'52192' b'51224' b'605420' b'79028' b'67956' b'5048'
 b'81188' b'70740' b'2720' b'184' b'811008' b'6724' b'7128' b'41732'
 b'446792' b'107676' b'438616' b'6640' b'810996' b'76108' b'71260'
 b'151976' b'52096' b'64764' b'60580' b'7324' b'3176' b'49604' b'57700'
 b'5092' b'52084' b'82940' b'62604' b'41352' b'41756' b'5552' b'41452'
 b'57776' b'84120' b'41216' b'10920' b'5724']
Feature: top_3_90_day_fresh_product
Tensor: [b'156' b'2312' b'1260' b'1264' b'176' b'1164' b'5744' b'1372' b'85104'
 b'77000' b'811428' b'3160' b'41452' b'33652' b'2116' b'77312' b'44'
 b'1448' b'7872' b'458128' b'2564' b'2124' b'NA' b'1172' b'3364' b'67940'
 b'14468' b'141704' b'188' b'88740' b'246112' b'100' b'2596' b'811020'
 b'3504' b'49808' b'74448' b'1376' b'37132' b'452352' b'2764' b'1532'
 b'73260' b'9264' b'54148' b'2500' b'5996' b'4416' b'1192' b'6936' b'2120'
 b'564952' b'7128' b'949664' b'62604' b'90676' b'82408' b'6640' b'41464'
 b'3048' b'1444' b'76108' b'8328' b'1180' b'2692' b'52' b'8764' b'48'
 b'77808' b'67956' b'9272' b'2316' b'87484' b'6716' b'65548' b'452304'
 b'93652' b'3080' b'67116' b'64128' b'148984' b'452324' b'1504' b'1408'
 b'65084' b'86792' b'49788' b'70372' b'110564' b'59128' b'49472' b'7732'
 b'65564' b'90068' b'264088' b'65144' b'41756' b'71800' b'52096' b'2376'
 b'41120' b'839900' b'438616' b'81188' b'103652' b'73008' b'9568'
 b'185620' b'74796' b'64132' b'87344' b'7324' b'235472' b'71260' b'3500'
 b'10920' b'68100' b'3356' b'41604' b'2720' b'41428' b'52108' b'3188'
 b'88576' b'4912' b'3376' b'41716' b'4828' b'452220' b'65568' b'9856'
 b'10652' b'581832' b'4224' b'3176' b'11908' b'98784' b'117632' b'4744'
 b'57692' b'68104' b'52156' b'2204' b'2320' b'3184' b'452368' b'49780'
 b'57700' b'65296' b'81764' b'41432' b'4348' b'5552' b'66104' b'452300'
 b'51224' b'121676' b'83576' b'2160' b'811024' b'555576' b'34484' b'6124']
Feature: top_4_90_day_fresh_product
Tensor: [b'176' b'1192' b'1264' b'100' b'49808' b'1164' b'74448' b'44' b'2120'
 b'214460' b'156' b'85104' b'811944' b'41768' b'1376' b'2692' b'3080'
 b'1260' b'52140' b'2116' b'48' b'188' b'52' b'2312' b'7732' b'NA' b'2764'
 b'5048' b'235472' b'3364' b'90068' b'3500' b'7324' b'4416' b'1372'
 b'14468' b'2316' b'10884' b'1532' b'6716' b'9856' b'3048' b'3160'
 b'462508' b'438616' b'1180' b'5744' b'9264' b'1444' b'3376' b'2564'
 b'14652' b'3176' b'1176' b'65568' b'41224' b'246112' b'11152' b'2124'
 b'1448' b'5752' b'3188' b'70376' b'77312' b'41120' b'1172' b'78432'
 b'4452' b'245720' b'65128' b'65884' b'787256' b'79064' b'8520' b'4912'
 b'2204' b'70176' b'8240' b'4744' b'71264' b'49776' b'7128' b'452304'
 b'839892' b'3504' b'5092' b'9272' b'54124' b'2500' b'66104' b'110564'
 b'41432' b'2720' b'6320' b'452252' b'7872' b'92116' b'66924' b'121676'
 b'49600' b'8244' b'452244' b'70424' b'65564' b'76108' b'3184' b'5568'
 b'2560' b'41324' b'65964' b'3732' b'6000' b'4828' b'74796' b'57776'
 b'41716' b'3168' b'8764' b'65548' b'811940' b'2596' b'6936' b'839900'
 b'452220' b'9568' b'8328' b'555576' b'6732' b'67956' b'61244' b'65384'
 b'93652' b'88740' b'41540' b'79080' b'41172' b'52156' b'251052' b'148984'
 b'37128' b'811192' b'49800' b'64132' b'67044' b'2324' b'78400' b'14672'
 b'49784' b'52108' b'5996' b'41428' b'555588' b'344784' b'5552' b'264088'
 b'10656' b'64020' b'11596' b'33708' b'452352' b'62604' b'5860' b'57708'
 b'811772' b'48028' b'564916' b'48772' b'49788' b'377356' b'556808'
 b'581832' b'65144' b'64764' b'8248' b'151976' b'2320' b'97240' b'1504'
 b'452300' b'107604' b'78388' b'37124']
Feature: top_5_90_day_fresh_product
Tensor: [b'1264' b'2316' b'176' b'44' b'1172' b'1260' b'7732' b'188' b'100'
 b'64132' b'78388' b'1444' b'156' b'6936' b'2120' b'65084' b'2312' b'1164'
 b'133116' b'41608' b'NA' b'93652' b'77312' b'74448' b'4452' b'2764' b'52'
 b'67116' b'2124' b'3160' b'2692' b'3504' b'4416' b'179940' b'2116'
 b'1372' b'1192' b'48' b'1176' b'1532' b'3080' b'452244' b'1376' b'452240'
 b'5552' b'52096' b'5744' b'6124' b'41120' b'41324' b'564916' b'1448'
 b'3364' b'64128' b'5752' b'811944' b'2564' b'3048' b'1180' b'3184'
 b'3500' b'2560' b'76108' b'57700' b'4828' b'52108' b'64656' b'4348'
 b'41716' b'452304' b'3860' b'41216' b'581832' b'811000' b'184' b'3188'
 b'3732' b'11596' b'78400' b'557876' b'41708' b'438616' b'5692' b'49788'
 b'2160' b'48636' b'86520' b'2320' b'8328' b'2500' b'71356' b'67940'
 b'8764' b'79028' b'41196' b'5996' b'51224' b'811076' b'54124' b'66308'
 b'9844' b'77244' b'41604' b'92396' b'7128' b'5860' b'90068' b'71792'
 b'33724' b'3176' b'3356' b'1504' b'65564' b'41428' b'768752' b'54148'
 b'839900' b'52140' b'810996' b'13416' b'65548' b'811772' b'11752'
 b'78432' b'199836' b'452300' b'48648' b'64968' b'787256' b'67576'
 b'41768' b'6640' b'246112' b'74796' b'59128' b'41756' b'108772' b'1156'
 b'6716' b'839892' b'2596' b'49488' b'49804' b'845268' b'206252' b'26792'
 b'110564' b'9568' b'41224' b'603460' b'65464' b'41724' b'185620' b'88576'
 b'88740' b'10920' b'70176' b'377356' b'811428' b'8168' b'149008' b'49388'
 b'12872' b'65144' b'33652' b'151976' b'49816' b'48012' b'14468' b'4744'
 b'6832' b'33644' b'41432' b'71260' b'214460' b'605148' b'41204' b'816568'
 b'77516' b'8244']
Feature: top_1_7_day_non_fresh_product
Tensor: [b'2192' b'124' b'1352' b'1356' b'1228' b'968504' b'8216' b'7424' b'1528'
 b'736296' b'245488' b'67624' b'51504' b'5616' b'59608' b'88' b'9956'
 b'40456' b'1332' b'2496' b'64616' b'3460' b'66460' b'11424' b'80460'
 b'2556' b'8500' b'10104' b'455536' b'1380' b'399060' b'19740' b'1276'
 b'4648' b'16696' b'37752' b'5344' b'28' b'1232' b'1560' b'2492' b'1184'
 b'45244' b'2572' b'771148' b'2412' b'60928' b'24' b'2860' b'NA' b'1516'
 b'4708' b'211568' b'2140' b'12672' b'1284' b'44796' b'2732' b'31068'
 b'1240' b'1424' b'1324' b'1452' b'4408' b'116796' b'2676' b'7152' b'3060'
 b'809012' b'14828' b'7108' b'64088' b'20' b'455204' b'48688' b'4748'
 b'36584' b'53648' b'118652' b'313612' b'210984' b'8388' b'3056' b'2188'
 b'4696' b'16600' b'1304' b'2776' b'25136' b'36328' b'75152' b'6348'
 b'57152' b'6156' b'25128' b'300016' b'1344' b'92344' b'8104' b'70340'
 b'6564' b'25108' b'70516' b'1328' b'7668' b'36568' b'1220' b'7224'
 b'8592' b'4104' b'3124' b'2132' b'116452' b'4328' b'3808' b'24816'
 b'915816' b'135372' b'51292' b'277808' b'49712' b'160' b'50552' b'2296'
 b'326180' b'16680' b'3532' b'2704' b'4160' b'583488' b'6356' b'1512'
 b'370204' b'4464' b'3976' b'3488' b'2488' b'6364' b'3596' b'1312'
 b'36504' b'818192' b'50636' b'4948' b'2568' b'2584' b'108' b'4564'
 b'84160' b'10756' b'65932' b'48664' b'2456' b'4924' b'12552' b'5388'
 b'490528' b'5672' b'70292' b'65812' b'3092' b'84652' b'956856' b'32'
 b'3200' b'2416' b'10808' b'51448' b'8556' b'41872' b'90236' b'557064'
 b'1216' b'447028' b'75124' b'84372' b'3236' b'3744' b'65428' b'1248'
 b'66564' b'9416' b'147824' b'32856' b'12136' b'2260' b'293556' b'11632'
 b'33180' b'33412' b'49756' b'90296' b'4016' b'4780' b'2552' b'3668'
 b'764628' b'26508' b'6944' b'1500' b'16668' b'3276' b'5596' b'45612'
 b'7176' b'216276' b'63380' b'5080' b'6612' b'95460' b'44480' b'74684'
 b'219788' b'7980' b'6052' b'11008' b'64228' b'25132' b'2112' b'2148'
 b'12556' b'4816' b'36444' b'15604' b'2240' b'95320' b'51864' b'3920'
 b'450356' b'989708' b'11836' b'77380' b'9544' b'957296' b'11732' b'10200'
 b'557748' b'908208' b'77908' b'57148' b'28376' b'168' b'103520' b'36852'
 b'14796' b'3784' b'1404' b'94716' b'103884' b'84' b'4196' b'251808' b'72'
 b'51620' b'92284' b'24980' b'4812' b'60944' b'2508' b'2256' b'9884'
 b'3484' b'83740' b'3720' b'7736' b'501784' b'83872' b'6512' b'776584'
 b'76' b'14480' b'136' b'961820' b'4192' b'6212' b'2280' b'64824' b'12204'
 b'16168' b'6748' b'3468' b'1360' b'113520' b'12532' b'10428' b'765808'
 b'8704' b'12176' b'4704' b'89560' b'62252' b'11432' b'7960' b'6664'
 b'5444' b'142452' b'5636' b'3144' b'5944' b'2688' b'1224' b'24836'
 b'3564' b'6380' b'17784' b'15920' b'3344' b'5688' b'2348' b'2208'
 b'51556' b'114072' b'68460' b'17528' b'3324' b'1552' b'17596' b'119164'
 b'65424' b'48608' b'8644' b'597344' b'65968' b'903488' b'12436' b'1252'
 b'3736' b'1368' b'52220' b'2848' b'95916' b'92164' b'65012' b'12544'
 b'7228' b'73408' b'2332' b'214472' b'77936' b'286488' b'68' b'31060'
 b'989268' b'1384' b'13636' b'373576' b'121212' b'1212' b'455356' b'44860'
 b'5508' b'40396' b'7712' b'2268' b'379780' b'3028' b'5404' b'14524'
 b'2304' b'24112' b'1556' b'65696' b'97332' b'6632' b'6816' b'10424'
 b'4880' b'33276' b'87020' b'5704' b'200112' b'273364' b'54988' b'454264'
 b'113336' b'6072' b'24932' b'96944' b'9132' b'2264' b'83596' b'64112'
 b'4520' b'1256' b'2248' b'6524' b'38512' b'22320' b'2520' b'25384'
 b'55156' b'2180' b'11052' b'8808' b'111148' b'809428' b'4560' b'5236'
 b'91612' b'306644' b'107352' b'2532']
Feature: top_2_7_day_non_fresh_product
Tensor: [b'51504' b'51716' b'65436' b'1352' b'2456' b'2492' b'1356' b'23944'
 b'2188' b'2192' b'5316' b'1764' b'4240' b'10104' b'1312' b'609960' b'124'
 b'22260' b'65932' b'2132' b'14804' b'557064' b'7668' b'57152' b'1424'
 b'8500' b'82400' b'1620' b'3600' b'28' b'1500' b'12556' b'2688' b'4816'
 b'2572' b'12176' b'2180' b'25108' b'68484' b'3668' b'2140' b'14756'
 b'17756' b'1560' b'4148' b'14764' b'2848' b'16800' b'173436' b'6668'
 b'114296' b'9344' b'2584' b'40456' b'1276' b'1512' b'6844' b'1184'
 b'3200' b'88' b'65828' b'1452' b'NA' b'149492' b'5080' b'48736' b'1360'
 b'8592' b'16132' b'44872' b'36764' b'19740' b'495964' b'31116' b'1284'
 b'4908' b'68' b'1588' b'4648' b'8216' b'1228' b'64136' b'65052' b'3092'
 b'1220' b'1612' b'7736' b'122012' b'66564' b'2520' b'6612' b'3276'
 b'3144' b'9308' b'42444' b'6348' b'2352' b'24' b'2296' b'4748' b'60856'
 b'3824' b'66088' b'44480' b'917780' b'11928' b'83900' b'10808' b'2516'
 b'968008' b'2416' b'2440' b'749928' b'11468' b'2412' b'951152' b'7108'
 b'1188' b'293556' b'68496' b'51444' b'764100' b'2148' b'4220' b'5084'
 b'399060' b'4520' b'3744' b'1272' b'596104' b'5136' b'8180' b'89028'
 b'20' b'300016' b'4524' b'10036' b'12136' b'45572' b'78504' b'2704'
 b'455536' b'98044' b'25132' b'49712' b'49732' b'3124' b'49760' b'2208'
 b'4408' b'1556' b'2176' b'28840' b'71452' b'3056' b'4276' b'5616'
 b'64680' b'61112' b'10756' b'31068' b'908208' b'4192' b'1344' b'19172'
 b'4572' b'64088' b'1368' b'6848' b'1232' b'4812' b'105632' b'56' b'2260'
 b'454264' b'36444' b'73076' b'54988' b'4000' b'4172' b'2676' b'67028'
 b'82364' b'76200' b'3084' b'1212' b'5056' b'1464' b'5348' b'65428'
 b'3516' b'2144' b'6352' b'1468' b'89688' b'36568' b'82244' b'11336'
 b'70516' b'83740' b'2860' b'3196' b'4564' b'2672' b'227156' b'8868'
 b'2508' b'12656' b'1536' b'66796' b'488608' b'25772' b'51620' b'173052'
 b'37928' b'4104' b'1404' b'2556' b'4196' b'597420' b'36852' b'12272'
 b'502228' b'65708' b'10896' b'8556' b'27232' b'11024' b'6356' b'2332'
 b'10992' b'94712' b'10064' b'11924' b'76' b'565772' b'7912' b'66460'
 b'785820' b'22160' b'184120' b'108936' b'2248' b'43932' b'8388' b'66448'
 b'14628' b'11512' b'3660' b'5960' b'6568' b'100696' b'7880' b'32'
 b'475956' b'2304' b'65816' b'66568' b'1332' b'1248' b'5704' b'80116'
 b'61064' b'823960' b'28368' b'908244' b'51292' b'65836' b'71428' b'2388'
 b'172' b'41872' b'76312' b'16600' b'2540' b'105900' b'816152' b'11236'
 b'20180' b'7224' b'12848' b'1244' b'3028' b'36824' b'21824' b'777220'
 b'12360' b'3344' b'14532' b'242756' b'51424' b'82604' b'64852' b'9956'
 b'3596' b'444016' b'5688' b'4040' b'784484' b'1436' b'9872' b'2624'
 b'12580' b'300012' b'955756' b'5116' b'3460' b'22916' b'176580' b'1324'
 b'1488' b'64056' b'4292' b'58312' b'36848' b'24984' b'42608' b'44884'
 b'988636' b'35988' b'108' b'11376' b'66956' b'5236' b'2512' b'66952'
 b'145892' b'63996' b'71440' b'761392' b'489120' b'51756' b'11200'
 b'530892' b'2484' b'43976' b'65664' b'71004' b'24816' b'40432' b'76144'
 b'1396' b'50876' b'48600' b'25128' b'5508' b'8960' b'1584' b'54976'
 b'70220' b'3236' b'10224' b'21512' b'12544' b'5636' b'10184' b'1328'
 b'57148' b'65916' b'49180' b'55380' b'7984' b'83132' b'3868' b'16536'
 b'19748' b'35452' b'964104' b'6132' b'65424' b'64824' b'916296' b'1240'
 b'108712' b'16748' b'66348' b'5444' b'12184' b'3524' b'43108' b'214408'
 b'91696' b'5232' b'11688' b'45204' b'48624' b'78848' b'43384' b'7492'
 b'7744' b'24784' b'1320' b'5592' b'51448' b'601476' b'3284' b'65684'
 b'70292' b'83460' b'9276' b'746308' b'70340' b'4936' b'4380' b'2348'
 b'375392' b'36912' b'42912' b'12380' b'93044' b'17596' b'67244' b'9544'
 b'551076' b'15920' b'2212' b'2532' b'54436' b'2732' b'4948' b'3108'
 b'750428' b'753992' b'6364' b'3476' b'144788' b'5984' b'36328' b'122672'
 b'1528' b'64664' b'1420' b'9408' b'84928' b'443368' b'24788' b'24116'
 b'5736' b'3920' b'1572' b'5676' b'203036' b'2292' b'79408' b'16' b'5332'
 b'34880' b'6156' b'8124' b'6452' b'3956' b'65812' b'279408' b'273356'
 b'537452' b'4160' b'3736' b'1460' b'737736' b'53684' b'6276' b'683160'
 b'46988' b'144' b'10892' b'1304' b'12704' b'24836' b'51752' b'65904'
 b'11880' b'3488' b'49664' b'7176' b'49448' b'3060' b'42612' b'819108'
 b'12436' b'6224' b'24940' b'120' b'49452' b'4016' b'3480' b'16696'
 b'2232']
Feature: top_3_7_day_non_fresh_product
Tensor: [b'3056' b'1284' b'86780' b'119632' b'118652' b'2624' b'2332' b'66312'
 b'2572' b'2732' b'41872' b'5736' b'1368' b'70312' b'51580' b'1312'
 b'66564' b'70516' b'1232' b'25108' b'65444' b'62080' b'965524' b'5616'
 b'1248' b'4220' b'66108' b'1352' b'6632' b'4816' b'1424' b'81096' b'2132'
 b'NA' b'24284' b'1356' b'11200' b'8500' b'54524' b'8960' b'2776' b'2492'
 b'1184' b'34580' b'5104' b'5316' b'2704' b'30292' b'12324' b'14480' b'32'
 b'1228' b'88' b'3476' b'7984' b'11924' b'3460' b'78436' b'54988' b'55048'
 b'1212' b'7816' b'108104' b'10896' b'2848' b'41864' b'77996' b'5388'
 b'7136' b'65172' b'124' b'1500' b'9884' b'1560' b'3720' b'315932' b'7152'
 b'9188' b'64596' b'8216' b'300016' b'108' b'1276' b'2192' b'2256'
 b'56896' b'51504' b'24804' b'16072' b'735820' b'538028' b'2772' b'16624'
 b'1596' b'51972' b'4192' b'82864' b'6348' b'19420' b'2496' b'94160'
 b'67364' b'29612' b'80024' b'3808' b'9432' b'2908' b'4748' b'19740'
 b'11052' b'834652' b'1344' b'583488' b'4948' b'5024' b'66476' b'64636'
 b'24816' b'6364' b'74440' b'76364' b'2260' b'40896' b'8172' b'762880'
 b'49664' b'1452' b'3236' b'102400' b'1360' b'1528' b'2520' b'2512'
 b'2540' b'951380' b'66940' b'9956' b'57616' b'274296' b'5084' b'999344'
 b'21776' b'12656' b'11220' b'3092' b'28840' b'160' b'7272' b'6032'
 b'16676' b'9200' b'3060' b'14760' b'51788' b'5360' b'2180' b'40620'
 b'14292' b'1268' b'12848' b'10448' b'4964' b'42488' b'17452' b'5080'
 b'12176' b'139840' b'83872' b'49684' b'41524' b'767708' b'2108' b'15608'
 b'8252' b'112988' b'10036' b'50848' b'6224' b'6156' b'7896' b'949800'
 b'3124' b'49672' b'139636' b'76404' b'780084' b'5244' b'2584' b'4300'
 b'66760' b'57084' b'4656' b'20' b'6356' b'2516' b'2680' b'19088'
 b'989268' b'51672' b'5624' b'10028' b'24188' b'3260' b'1240' b'1456'
 b'151936' b'51372' b'5872' b'7632' b'2412' b'2556' b'913772' b'454264'
 b'813516' b'57540' b'43024' b'2688' b'6784' b'4240' b'3596' b'64056'
 b'10428' b'65052' b'5664' b'66348' b'4700' b'3668' b'65836' b'1612'
 b'5596' b'6292' b'682264' b'10624' b'2296' b'71500' b'2588' b'4408'
 b'1244' b'6568' b'1220' b'949872' b'4704' b'3344' b'3964' b'66460'
 b'3744' b'3600' b'455536' b'2568' b'293556' b'2608' b'908208' b'2208'
 b'12136' b'42544' b'2144' b'3488' b'67624' b'81296' b'65096' b'5232'
 b'10092' b'41544' b'67704' b'7668' b'2860' b'2244' b'64664' b'1336'
 b'76708' b'67444' b'3200' b'27300' b'31068' b'8560' b'1304' b'25748'
 b'12544' b'10116' b'5332' b'48276' b'33044' b'4648' b'4164' b'27072'
 b'4196' b'73540' b'86924' b'28' b'287820' b'4104' b'91936' b'11872'
 b'117756' b'11660' b'764728' b'79408' b'2388' b'68484' b'51660' b'1584'
 b'1468' b'3144' b'6132' b'4464' b'5704' b'5076' b'56136' b'76' b'7224'
 b'3816' b'36444' b'2232' b'51752' b'11836' b'60944' b'100308' b'60856'
 b'99648' b'88064' b'65488' b'24912' b'592792' b'1200' b'12636' b'65452'
 b'1188' b'48736' b'22320' b'65524' b'5508' b'35772' b'2488' b'191112'
 b'2136' b'587804' b'7492' b'234828' b'25116' b'5312' b'561804' b'6452'
 b'7436' b'48412' b'5344' b'4988' b'14524' b'2148' b'21336' b'6380'
 b'6664' b'55000' b'13824' b'7720' b'68' b'55064' b'5464' b'365544'
 b'9628' b'68304' b'8384' b'51292' b'5004' b'16264' b'184120' b'4112'
 b'64888' b'67508' b'3228' b'65828' b'561488' b'682952' b'47852' b'66796'
 b'60444' b'12204' b'67976' b'41040' b'2504' b'33276' b'75928' b'95320'
 b'215712' b'65016' b'234124' b'51564' b'60940' b'16536' b'65932' b'4036'
 b'8600' b'344412' b'9780' b'80216' b'65872' b'54520' b'233732' b'8592'
 b'8488' b'2416' b'36504' b'84144' b'5228' b'96776' b'65824' b'10808'
 b'63996' b'10348' b'21912' b'4480' b'2696' b'24916' b'9320' b'5636'
 b'767868' b'12056' b'25772' b'908212' b'400992' b'23988' b'24792' b'4152'
 b'7068' b'89756' b'2352' b'16652' b'946776' b'6204' b'2524' b'4328'
 b'66700' b'8300' b'2348' b'82836' b'18448' b'465656' b'125324' b'7532'
 b'9504' b'3660' b'40584' b'36' b'25784' b'74916' b'49756' b'955768'
 b'81828' b'582564' b'1320' b'965600' b'3796' b'12716' b'601476' b'17436'
 b'6848' b'22100' b'2140' b'25684' b'10104' b'42876' b'63016' b'34600'
 b'55228' b'30816' b'67552' b'44412' b'6212' b'64748' b'5444' b'2152'
 b'5960' b'9408' b'14764' b'20812' b'21944' b'59332' b'2864' b'3700'
 b'3096' b'1572' b'55332' b'187560' b'51840' b'48408' b'9908' b'12404'
 b'7108' b'3880' b'444016' b'49552' b'12360' b'4936' b'55172' b'71128'
 b'44588' b'9496' b'8204' b'87196' b'86380' b'2460' b'547432' b'51444'
 b'606420' b'1548' b'170900' b'108972' b'78032' b'51756' b'108812'
 b'11976' b'4520' b'23408' b'75124' b'528252' b'295104' b'59624' b'12200'
 b'9360' b'4172' b'60752' b'1556' b'1552' b'739472' b'6952' b'97408'
 b'1224' b'4276' b'71148' b'5184' b'1324' b'4176']
Feature: top_4_7_day_non_fresh_product
Tensor: [b'51444' b'5056' b'2624' b'1500' b'88' b'55128' b'10260' b'79604'
 b'65932' b'3200' b'51504' b'6380' b'5344' b'3056' b'64824' b'2412'
 b'1356' b'1464' b'66460' b'1424' b'83740' b'65336' b'14760' b'1244'
 b'124' b'2280' b'7080' b'300016' b'36584' b'41548' b'28' b'16696' b'NA'
 b'36836' b'1452' b'4116' b'99648' b'49676' b'50876' b'12056' b'4408'
 b'2416' b'62732' b'2492' b'7876' b'38164' b'5080' b'7108' b'57164'
 b'51348' b'173052' b'5636' b'1232' b'1228' b'37752' b'10428' b'2556'
 b'5736' b'122680' b'118652' b'97792' b'8388' b'2192' b'142952' b'3464'
 b'1312' b'40360' b'65428' b'12668' b'17596' b'7736' b'4816' b'1368'
 b'2572' b'11168' b'3660' b'12136' b'40412' b'7224' b'10036' b'10756'
 b'682264' b'1304' b'175588' b'28368' b'2672' b'2296' b'57152' b'66564'
 b'2332' b'16224' b'24788' b'5920' b'2408' b'1184' b'749048' b'1344'
 b'5228' b'67508' b'4696' b'175948' b'2460' b'27208' b'1284' b'2732'
 b'24836' b'85296' b'4560' b'34880' b'3124' b'914476' b'4948' b'11884'
 b'3120' b'3808' b'23012' b'17756' b'5992' b'9456' b'2132' b'1276' b'1560'
 b'771140' b'1240' b'6348' b'8252' b'300012' b'84720' b'38148' b'68372'
 b'4196' b'14756' b'2512' b'958324' b'11664' b'97408' b'66108' b'11924'
 b'5704' b'2352' b'105744' b'22308' b'3744' b'64828' b'3100' b'11224'
 b'1352' b'71188' b'450748' b'90708' b'51372' b'36444' b'9344' b'66492'
 b'2704' b'7984' b'6156' b'9924' b'1404' b'14524' b'6452' b'3084' b'3484'
 b'55532' b'5624' b'32920' b'37916' b'1324' b'15944' b'21912' b'5688'
 b'14480' b'905692' b'721788' b'16536' b'64088' b'2676' b'62252' b'8592'
 b'562740' b'24896' b'52536' b'65888' b'7816' b'464592' b'8216' b'5000'
 b'3392' b'3276' b'51972' b'583288' b'11944' b'15816' b'2180' b'3144'
 b'5576' b'743952' b'68560' b'120872' b'949656' b'14764' b'9628' b'105900'
 b'65424' b'48952' b'74916' b'11424' b'7492' b'55348' b'3196' b'2568'
 b'35440' b'8920' b'3920' b'2532' b'10412' b'110196' b'84160' b'3596'
 b'6072' b'2188' b'106840' b'48408' b'62636' b'8500' b'58920' b'2144'
 b'462960' b'2776' b'2456' b'110144' b'15920' b'449588' b'7500' b'4800'
 b'6032' b'5084' b'24' b'4520' b'2848' b'1248' b'103984' b'24912' b'6356'
 b'8408' b'12096' b'41512' b'24000' b'5116' b'3108' b'12544' b'16456'
 b'28356' b'3060' b'565168' b'2868' b'7436' b'1516' b'10808' b'12176'
 b'68028' b'116' b'111608' b'3024' b'749300' b'15228' b'38160' b'1280'
 b'11976' b'5136' b'108' b'64636' b'9504' b'66204' b'64888' b'53688'
 b'50552' b'1027164' b'54044' b'56592' b'3460' b'4364' b'94812' b'196'
 b'41496' b'22232' b'1220' b'7572' b'10092' b'4192' b'56468' b'19172'
 b'2588' b'3616' b'11848' b'913772' b'22208' b'732280' b'4692' b'4700'
 b'5444' b'2908' b'4936' b'95160' b'948188' b'953008' b'10564' b'57116'
 b'489216' b'45572' b'2252' b'80880' b'74700' b'28344' b'2440' b'59300'
 b'4484' b'36312' b'43528' b'118412' b'7704' b'10104' b'5776' b'68484'
 b'2860' b'2584' b'6456' b'45204' b'12704' b'4172' b'912528' b'68'
 b'65496' b'603544' b'36848' b'2108' b'955216' b'4488' b'36488' b'82836'
 b'84652' b'42168' b'6364' b'76' b'2772' b'4924' b'78208' b'1556' b'45080'
 b'1272' b'394232' b'41516' b'48600' b'10596' b'7608' b'12012' b'48704'
 b'23988' b'25684' b'11200' b'66448' b'22476' b'88224' b'9408' b'64468'
 b'175644' b'1212' b'63996' b'31112' b'55904' b'60440' b'25128' b'466728'
 b'20264' b'20056' b'70476' b'51292' b'10896' b'54920' b'96672' b'5248'
 b'12556' b'65452' b'1320' b'5508' b'730552' b'185024' b'405768' b'12436'
 b'250384' b'5960' b'37652' b'9956' b'2508' b'95584' b'2348' b'490528'
 b'455204' b'1528' b'114356' b'62776' b'52492' b'51756' b'10384' b'3668'
 b'16236' b'81644' b'147844' b'83900' b'57024' b'1460' b'823924' b'7072'
 b'6612' b'1396' b'74788' b'196688' b'2260' b'68252' b'57244' b'67688'
 b'227660' b'37928' b'7832' b'66452' b'48348' b'64728' b'35956' b'10832'
 b'6664' b'488608' b'3468' b'14628' b'67708' b'7084' b'16800' b'41872'
 b'3600' b'6984' b'537084' b'40672' b'16144' b'211816' b'42600' b'4380'
 b'8384' b'82856' b'5312' b'79356' b'54988' b'3488' b'2488' b'2552'
 b'501788' b'91280' b'754876' b'962076' b'82320' b'9140' b'11488' b'10868'
 b'6120' b'40844' b'164' b'40248' b'75820' b'5004' b'597460' b'2520'
 b'9768' b'965604' b'9024' b'12204' b'12264' b'4356' b'63016' b'601492'
 b'21672' b'84336' b'56848' b'73408' b'32904' b'42884' b'76768' b'57556'
 b'48304' b'71004' b'8176' b'2256' b'22100' b'6288' b'6276' b'21276'
 b'5244' b'6792' b'106456' b'6104' b'80780' b'2148' b'31068' b'4760'
 b'10792' b'15652' b'3096' b'25748' b'17716' b'2112' b'187684' b'81296'
 b'77960' b'10480' b'67412' b'12412' b'112040' b'2872' b'32956' b'48852'
 b'71160' b'25696' b'79408' b'47464' b'16668' b'11432' b'12272' b'610392'
 b'331880' b'11480' b'908208' b'2484' b'588196' b'8756' b'97980' b'5464'
 b'74416' b'968940' b'454504' b'3612' b'77080' b'226108' b'73340' b'45796'
 b'70428' b'115332' b'17424' b'957504' b'448748' b'17452' b'949872'
 b'73232' b'10064' b'7412' b'776856' b'9908' b'12456' b'2304' b'68328'
 b'2176' b'41524' b'7424' b'2688' b'9224']
Feature: top_5_7_day_non_fresh_product
Tensor: [b'88' b'6212' b'65452' b'2460' b'1356' b'NA' b'14724' b'82084' b'1352'
 b'3488' b'944924' b'7272' b'100808' b'12552' b'12176' b'2572' b'2508'
 b'3144' b'2188' b'681956' b'2624' b'1516' b'989736' b'1452' b'1220'
 b'3596' b'4572' b'9780' b'1424' b'67000' b'86960' b'1312' b'2492'
 b'64252' b'54436' b'10208' b'112' b'49680' b'48664' b'571896' b'4948'
 b'2192' b'65012' b'105744' b'14760' b'44480' b'41872' b'5992' b'75124'
 b'60960' b'65288' b'1284' b'2456' b'64088' b'64100' b'16160' b'10092'
 b'300016' b'124' b'2608' b'19664' b'2412' b'4812' b'6348' b'2704'
 b'71128' b'445108' b'31112' b'51292' b'7876' b'2772' b'12324' b'4172'
 b'36828' b'92352' b'78884' b'43860' b'15608' b'11432' b'66760' b'1328'
 b'3964' b'1304' b'173416' b'2688' b'78052' b'9416' b'501788' b'25128'
 b'55128' b'52460' b'76' b'6816' b'3868' b'1276' b'2672' b'5232' b'67512'
 b'9188' b'64596' b'1252' b'41596' b'2676' b'2540' b'3744' b'3056' b'2280'
 b'2132' b'966320' b'8212' b'42484' b'1500' b'16072' b'113580' b'5080'
 b'3644' b'242756' b'3736' b'3200' b'9368' b'24584' b'37652' b'41584'
 b'6292' b'9472' b'2256' b'3720' b'4268' b'2556' b'6352' b'8444' b'57084'
 b'193816' b'14808' b'59580' b'3880' b'37936' b'5736' b'1232' b'3660'
 b'3392' b'80460' b'908208' b'146088' b'9504' b'3808' b'108104' b'4040'
 b'65060' b'3468' b'51304' b'66476' b'843404' b'60440' b'55396' b'36848'
 b'53688' b'74416' b'10276' b'106456' b'11024' b'8048' b'7560' b'10412'
 b'3028' b'7140' b'66460' b'24228' b'8500' b'8216' b'71120' b'9956'
 b'60456' b'4408' b'9884' b'65096' b'7716' b'3668' b'5988' b'54508'
 b'2296' b'28376' b'65248' b'66376' b'363420' b'14732' b'557064' b'65260'
 b'68500' b'64824' b'10892' b'48408' b'60856' b'14376' b'5476' b'4192'
 b'12516' b'20752' b'3124' b'23176' b'12636' b'6240' b'1416' b'1228'
 b'73232' b'40396' b'10756' b'406932' b'70544' b'2524' b'59840' b'173052'
 b'9792' b'399060' b'67988' b'10480' b'35448' b'49164' b'3436' b'2872'
 b'6612' b'65836' b'27208' b'60388' b'110200' b'761164' b'4196' b'17756'
 b'2632' b'176976' b'51568' b'120872' b'9436' b'817352' b'6512' b'8768'
 b'3096' b'80508' b'823924' b'3060' b'36764' b'450340' b'18152' b'4540'
 b'7548' b'10616' b'3092' b'6568' b'60708' b'5184' b'8408' b'13520'
 b'16732' b'1404' b'66040' b'12260' b'4104' b'115616' b'65824' b'25108'
 b'86116' b'81328' b'7712' b'3516' b'764028' b'3344' b'8868' b'2440'
 b'51504' b'17436' b'3700' b'1280' b'70744' b'537168' b'3564' b'80776'
 b'42076' b'35520' b'2512' b'8556' b'4240' b'2588' b'107352' b'71428'
 b'183896' b'88168' b'65492' b'54456' b'65828' b'12360' b'4148' b'7736'
 b'5056' b'6452' b'15920' b'2516' b'250384' b'2464' b'42488' b'36836'
 b'64084' b'11000' b'48412' b'77848' b'10808' b'44492' b'2732' b'57152'
 b'64616' b'1560' b'5576' b'6276' b'5700' b'9324' b'4524' b'6188' b'1256'
 b'64056' b'3920' b'550912' b'80536' b'70820' b'90404' b'19172' b'78308'
 b'7936' b'5308' b'120' b'65428' b'2520' b'7224' b'68512' b'20000'
 b'56584' b'45248' b'176164' b'26404' b'11848' b'24940' b'775664' b'5008'
 b'213436' b'10420' b'7764' b'28652' b'104' b'4564' b'3476' b'3480'
 b'949832' b'4960' b'51444' b'3444' b'454264' b'227660' b'6156' b'64680'
 b'147844' b'42176' b'9680' b'60944' b'2776' b'21668' b'105428' b'586936'
 b'36312' b'79536' b'49536' b'77892' b'70624' b'2292' b'12056' b'46036'
 b'65932' b'205884' b'160' b'5704' b'44412' b'35240' b'84488' b'16696'
 b'3032' b'65916' b'24816' b'54524' b'17196' b'10320' b'84016' b'5116'
 b'66680' b'601476' b'51676' b'45612' b'66564' b'7424' b'89136' b'821476'
 b'26628' b'12780' b'67704' b'60556' b'1324' b'2112' b'303504' b'28608'
 b'68316' b'51584' b'7984' b'5228' b'102292' b'5652' b'2304' b'6132'
 b'732280' b'99288' b'70368' b'70516' b'28404' b'22204' b'183168' b'8600'
 b'91936' b'488608' b'2860' b'4164' b'8452' b'3108' b'10428' b'86348'
 b'595828' b'9360' b'3824' b'5332' b'70332' b'78092' b'442208' b'76764'
 b'9868' b'188248' b'51752' b'75160' b'76816' b'42336' b'12556' b'16544'
 b'2584' b'7744' b'6204' b'33276' b'70784' b'207048' b'65860' b'22288'
 b'2956' b'1224' b'40680' b'65804' b'5136' b'28348' b'65432' b'8384'
 b'2108' b'4816' b'1512' b'473168' b'14480' b'11560' b'5924' b'55620'
 b'956856' b'113544' b'842888' b'125220' b'34600' b'16272' b'56460'
 b'1568' b'3276' b'83872' b'7072' b'7584' b'70364' b'15952' b'17452'
 b'15960' b'5244' b'68560' b'27212' b'9040' b'40636' b'49448' b'947460'
 b'609960' b'2348' b'64000' b'105900' b'64228' b'66108' b'57760' b'70888'
 b'6068' b'92472' b'78408' b'7528' b'9756' b'41516' b'10028' b'7108'
 b'11160' b'66312' b'136' b'5596' b'8064' b'68460' b'4520' b'76412'
 b'62080' b'4700' b'436632' b'97408' b'3976' b'66016' b'614084' b'5032'
 b'5508' b'421128' b'108296' b'74700' b'44404' b'551076' b'757168' b'5240'
 b'695320' b'28700' b'66304' b'88064' b'1548' b'47592' b'26356' b'36444'
 b'22356' b'450748' b'9820' b'11696' b'13884' b'7436' b'737940' b'12088'
 b'573900' b'990568' b'9408' b'832488' b'147112' b'94460' b'36568'
 b'74640' b'176692' b'43712' b'42392' b'960788' b'113312' b'2260' b'52000'
 b'17680' b'32832' b'8896' b'103080' b'74440' b'3460' b'4160' b'12656'
 b'103300' b'9600' b'5076' b'192600' b'50644' b'2708' b'105184' b'12676'
 b'65688' b'36580' b'5616' b'10684']
Feature: top_1_15_day_non_fresh_product
Tensor: [b'2192' b'124' b'1352' b'1356' b'2456' b'968504' b'82084' b'2188'
 b'956856' b'1528' b'736296' b'245488' b'67624' b'51504' b'2132' b'4172'
 b'557064' b'88' b'57152' b'9140' b'97792' b'2496' b'64616' b'3600'
 b'1312' b'1500' b'66460' b'11424' b'54436' b'10208' b'8500' b'10104'
 b'1380' b'1184' b'399060' b'1276' b'4648' b'16696' b'17756' b'5344'
 b'1560' b'1232' b'14764' b'2492' b'108104' b'45244' b'2572' b'771148'
 b'1228' b'2412' b'60928' b'24' b'28' b'813520' b'1516' b'8592' b'2140'
 b'12672' b'49552' b'44796' b'2732' b'31068' b'565672' b'1424' b'1324'
 b'1452' b'4408' b'11664' b'54316' b'41548' b'809012' b'14828' b'7108'
 b'64088' b'20' b'455204' b'52652' b'48688' b'7736' b'53648' b'2520'
 b'3200' b'64252' b'66476' b'8388' b'53032' b'6364' b'7152' b'44480'
 b'36328' b'8172' b'6348' b'25128' b'300016' b'92344' b'1284' b'8104'
 b'65932' b'6564' b'25108' b'70516' b'1328' b'7668' b'764100' b'7224'
 b'150304' b'6032' b'116452' b'4328' b'3808' b'1272' b'2352' b'24816'
 b'3276' b'277808' b'1304' b'10808' b'12136' b'22320' b'83872' b'326180'
 b'14628' b'193816' b'959932' b'3532' b'9956' b'2704' b'8252' b'65904'
 b'278172' b'583488' b'2256' b'370204' b'4464' b'3976' b'3488' b'743952'
 b'61112' b'10756' b'209364' b'74916' b'55348' b'3196' b'51292' b'3880'
 b'4816' b'56' b'1332' b'818192' b'2260' b'4948' b'2568' b'2584' b'108'
 b'4564' b'6568' b'84160' b'5348' b'12552' b'3668' b'490528' b'5672'
 b'70292' b'65812' b'3092' b'84652' b'2416' b'3344' b'51448' b'41872'
 b'1216' b'455536' b'447028' b'488608' b'84372' b'3236' b'5240' b'3744'
 b'65428' b'66564' b'173052' b'9416' b'13680' b'147824' b'36504' b'502228'
 b'2556' b'65096' b'293556' b'160' b'11632' b'33180' b'49756' b'90296'
 b'3460' b'4780' b'41864' b'785820' b'22160' b'5576' b'5444' b'96600'
 b'27072' b'3144' b'1512' b'216276' b'26404' b'597840' b'80536' b'2676'
 b'6612' b'36568' b'95460' b'68196' b'219788' b'7980' b'5076' b'982088'
 b'64228' b'37684' b'25132' b'2148' b'12556' b'16600' b'11236' b'2860'
 b'164' b'3920' b'989708' b'48736' b'577000' b'77380' b'9544' b'957296'
 b'11732' b'539436' b'557748' b'908208' b'77908' b'4160' b'5080' b'168'
 b'581988' b'592792' b'103520' b'8384' b'63120' b'84' b'10896' b'89136'
 b'72' b'24980' b'18196' b'4812' b'3056' b'60944' b'2508' b'9884' b'3484'
 b'83740' b'3720' b'501784' b'28200' b'776584' b'1240' b'14480' b'1404'
 b'4192' b'6212' b'2280' b'64824' b'12204' b'24836' b'1456' b'1360'
 b'1548' b'9344' b'113520' b'12532' b'10428' b'65828' b'12176' b'54976'
 b'11944' b'2112' b'6664' b'6156' b'68304' b'142452' b'5636' b'57148'
 b'1224' b'3564' b'65916' b'5136' b'5688' b'42600' b'5616' b'2208'
 b'51556' b'12544' b'114072' b'16748' b'17528' b'12184' b'66796' b'11560'
 b'119164' b'91696' b'6104' b'51716' b'11488' b'597344' b'147572' b'12436'
 b'1252' b'3124' b'1368' b'52220' b'7584' b'1268' b'7492' b'95916'
 b'92164' b'32' b'65012' b'42912' b'73408' b'17596' b'76' b'77936'
 b'18948' b'68' b'44412' b'989268' b'9756' b'4104' b'373576' b'121212'
 b'753992' b'99648' b'1212' b'455356' b'44860' b'9012' b'7712' b'2268'
 b'379780' b'3028' b'5404' b'2304' b'24112' b'5736' b'11848' b'65696'
 b'97332' b'7896' b'444016' b'10424' b'12360' b'33276' b'6452' b'414468'
 b'71128' b'87020' b'2296' b'54988' b'454264' b'6072' b'9040' b'573900'
 b'1460' b'96944' b'2288' b'2264' b'83596' b'64112' b'60904' b'4520'
 b'6524' b'45796' b'3516' b'448748' b'782776' b'55156' b'37752' b'49448'
 b'8808' b'819108' b'809428' b'4560' b'6224' b'5236' b'48408' b'3736'
 b'65288' b'306644' b'10320' b'2532' b'7424' b'2244']
Feature: top_2_15_day_non_fresh_product
Tensor: [b'51504' b'51716' b'65436' b'1352' b'1228' b'2492' b'1356' b'41552'
 b'5844' b'1764' b'4240' b'10104' b'1312' b'609960' b'124' b'66564'
 b'70516' b'2188' b'66460' b'7668' b'62080' b'1424' b'88' b'8500' b'1284'
 b'1332' b'835436' b'60904' b'81096' b'1500' b'12556' b'80460' b'4816'
 b'2572' b'12176' b'8960' b'6348' b'25108' b'2416' b'3668' b'41872'
 b'14756' b'37752' b'28' b'4196' b'300012' b'1560' b'3460' b'97792'
 b'173436' b'36824' b'1184' b'142952' b'5988' b'40456' b'1276' b'74704'
 b'31112' b'60856' b'65828' b'2860' b'2584' b'3720' b'66088' b'2280'
 b'5240' b'64596' b'10756' b'300016' b'12204' b'482992' b'3200' b'2296'
 b'44872' b'503952' b'24804' b'565592' b'65688' b'3344' b'78672' b'16624'
 b'2676' b'7152' b'70784' b'2456' b'82864' b'19664' b'2132' b'1620'
 b'65052' b'3092' b'2192' b'4748' b'6612' b'118652' b'210984' b'5992'
 b'67412' b'57152' b'32' b'3056' b'2352' b'1240' b'4692' b'66476' b'16600'
 b'1304' b'917780' b'40896' b'75152' b'6452' b'2516' b'2440' b'102400'
 b'24' b'4656' b'2412' b'3744' b'51672' b'8560' b'70340' b'7108' b'965524'
 b'31068' b'10792' b'36568' b'989584' b'10276' b'453164' b'8592' b'414180'
 b'3124' b'16676' b'4520' b'10036' b'70444' b'9040' b'135372' b'50876'
 b'1324' b'20' b'4524' b'49712' b'160' b'5688' b'50552' b'45572' b'583488'
 b'2704' b'455536' b'4408' b'49732' b'348700' b'6356' b'2732' b'2176'
 b'4480' b'71452' b'139872' b'14764' b'4276' b'5616' b'5344' b'68560'
 b'2488' b'6364' b'1344' b'766544' b'64088' b'173052' b'1368' b'399060'
 b'455204' b'68512' b'3920' b'9036' b'105632' b'1452' b'NA' b'50636'
 b'2256' b'454264' b'36444' b'73076' b'54988' b'4172' b'67028' b'82364'
 b'76200' b'2776' b'907328' b'48664' b'2608' b'449588' b'5664' b'65428'
 b'5388' b'6352' b'65836' b'1468' b'5596' b'89688' b'51444' b'24912'
 b'81596' b'11336' b'2140' b'957420' b'8624' b'3196' b'4704' b'73268'
 b'227156' b'1232' b'8556' b'90236' b'1536' b'1456' b'66796' b'68028'
 b'4924' b'2688' b'3564' b'2144' b'115876' b'65932' b'87612' b'1420'
 b'17756' b'36852' b'12552' b'65708' b'73244' b'5736' b'2508' b'33412'
 b'49760' b'5432' b'11924' b'1220' b'5080' b'2552' b'565772' b'10808'
 b'6132' b'2540' b'59620' b'33044' b'3276' b'37552' b'18448' b'43932'
 b'54044' b'67552' b'766024' b'11512' b'153472' b'5960' b'6568' b'8064'
 b'3096' b'475956' b'2304' b'65816' b'66568' b'44480' b'5704' b'74684'
 b'61064' b'2848' b'6052' b'51292' b'3488' b'24940' b'71428' b'2672'
 b'2388' b'11344' b'123432' b'27256' b'1584' b'4564' b'816152' b'2240'
 b'7224' b'12848' b'592792' b'9188' b'450356' b'1244' b'8388' b'12360'
 b'1360' b'7716' b'10892' b'10200' b'45080' b'82604' b'83740' b'444016'
 b'561804' b'7492' b'57148' b'4040' b'48704' b'184120' b'28376' b'14524'
 b'1436' b'16696' b'3468' b'3784' b'5508' b'8424' b'365544' b'8384'
 b'103884' b'2556' b'251808' b'58312' b'36848' b'24984' b'97376' b'9956'
 b'35988' b'41040' b'10428' b'67976' b'5228' b'2512' b'2504' b'33276'
 b'7984' b'145892' b'64824' b'63996' b'6512' b'776524' b'51756' b'15920'
 b'16536' b'3596' b'530892' b'2484' b'10384' b'43976' b'71004' b'80656'
 b'6748' b'3060' b'64096' b'48600' b'233732' b'25116' b'108' b'3144'
 b'19740' b'765808' b'82836' b'89560' b'62252' b'251884' b'2168' b'10224'
 b'16236' b'5444' b'12544' b'7080' b'7856' b'10184' b'970944' b'7744'
 b'2696' b'11468' b'24916' b'51372' b'83132' b'3868' b'6380' b'6100'
 b'1256' b'964104' b'65424' b'1516' b'17104' b'68460' b'66348' b'3028'
 b'3324' b'1552' b'1280' b'17596' b'214408' b'5672' b'5232' b'8644'
 b'182520' b'85456' b'1320' b'65968' b'903488' b'11848' b'601476' b'3284'
 b'3736' b'70292' b'66620' b'9276' b'746308' b'55440' b'965600' b'4380'
 b'59580' b'48264' b'1404' b'375392' b'60444' b'6968' b'5576' b'7228'
 b'67244' b'214472' b'286488' b'84356' b'4948' b'17468' b'1272' b'13636'
 b'11424' b'10028' b'613884' b'612080' b'144788' b'59332' b'9224'
 b'193264' b'11432' b'64664' b'9408' b'24788' b'24116' b'6032' b'1572'
 b'5676' b'203036' b'74916' b'6816' b'24640' b'16' b'724144' b'8124'
 b'3956' b'65812' b'8920' b'200112' b'273364' b'51284' b'749048' b'4160'
 b'24932' b'170900' b'737736' b'9132' b'6276' b'683160' b'48556' b'957816'
 b'502356' b'24836' b'4956' b'65904' b'31116' b'2260' b'49664' b'234984'
 b'11052' b'20984' b'913732' b'12436' b'1224' b'557344' b'91612' b'4812'
 b'4016' b'107352' b'14584' b'2112']
Feature: top_3_15_day_non_fresh_product
Tensor: [b'88' b'1284' b'65452' b'119632' b'118652' b'2624' b'1352' b'76' b'2572'
 b'7424' b'3488' b'66088' b'70312' b'51580' b'1312' b'2508' b'65932'
 b'1228' b'94472' b'65444' b'59608' b'66564' b'65336' b'14760' b'1244'
 b'5616' b'2732' b'1620' b'66108' b'1424' b'108948' b'1356' b'1232'
 b'2488' b'949352' b'2556' b'11200' b'8500' b'54524' b'455536' b'2132'
 b'19740' b'62732' b'1368' b'5316' b'14764' b'2704' b'173052' b'32'
 b'9376' b'6452' b'590676' b'5312' b'65428' b'4564' b'78436' b'55048'
 b'4948' b'3108' b'114296' b'9344' b'6348' b'41864' b'77996' b'24816'
 b'1512' b'6844' b'1184' b'3200' b'124' b'1500' b'11168' b'1560' b'1404'
 b'19068' b'3056' b'67216' b'5080' b'11432' b'293556' b'16132' b'86780'
 b'5812' b'2688' b'56896' b'16800' b'NA' b'6816' b'538028' b'2772' b'3736'
 b'61220' b'51784' b'27296' b'331880' b'1240' b'64596' b'7224' b'2492'
 b'3744' b'51504' b'1220' b'1452' b'300016' b'80024' b'550912' b'9432'
 b'36584' b'82836' b'7720' b'1344' b'583488' b'24' b'4696' b'300012'
 b'64636' b'57084' b'60856' b'41872' b'56592' b'59580' b'25136' b'74700'
 b'57152' b'42424' b'2348' b'1276' b'94160' b'146088' b'749928' b'10296'
 b'2520' b'56472' b'1304' b'11224' b'24836' b'2140' b'3144' b'68496'
 b'3392' b'51444' b'73276' b'12336' b'2148' b'160' b'548824' b'171184'
 b'10412' b'7108' b'399060' b'5100' b'28' b'596104' b'40456' b'1332'
 b'2192' b'81096' b'32920' b'57116' b'4964' b'10036' b'9036' b'68484'
 b'613884' b'49684' b'25132' b'8644' b'51372' b'4520' b'14732' b'112988'
 b'3336' b'14524' b'2332' b'2208' b'2172' b'7896' b'78876' b'4408' b'3124'
 b'5184' b'76404' b'5244' b'2584' b'7492' b'64680' b'31068' b'909888'
 b'2456' b'4572' b'989268' b'5624' b'964960' b'45440' b'76808' b'65892'
 b'151936' b'20' b'5872' b'786164' b'761164' b'4816' b'454264' b'4000'
 b'43024' b'9436' b'3564' b'2392' b'3084' b'68304' b'2412' b'52004'
 b'7712' b'10428' b'450340' b'7500' b'65436' b'6568' b'7608' b'5084'
 b'12324' b'1612' b'5596' b'682264' b'82464' b'82244' b'11800' b'2588'
 b'70516' b'83740' b'15840' b'4704' b'948284' b'97792' b'2676' b'8868'
 b'12656' b'2568' b'328828' b'66460' b'75124' b'25772' b'9544' b'2608'
 b'7736' b'908208' b'1248' b'3476' b'11768' b'4700' b'32856' b'76588'
 b'104868' b'5028' b'10092' b'2516' b'7668' b'2244' b'64664' b'2672'
 b'54988' b'10992' b'67444' b'3480' b'10064' b'4016' b'6632' b'4196'
 b'80460' b'64952' b'4148' b'2872' b'488872' b'8216' b'5344' b'557064'
 b'16668' b'6156' b'64088' b'16536' b'45612' b'4936' b'66448' b'91936'
 b'11872' b'8552' b'3060' b'764728' b'2388' b'1468' b'120' b'59300'
 b'43528' b'908244' b'12176' b'555808' b'20152' b'34380' b'2352' b'24940'
 b'64004' b'557344' b'3596' b'2540' b'3092' b'105900' b'71296' b'10956'
 b'24912' b'2108' b'603544' b'12056' b'12636' b'1188' b'2860' b'8252'
 b'2256' b'5508' b'16176' b'60944' b'191112' b'2136' b'14532' b'7804'
 b'11708' b'84' b'1224' b'586936' b'9956' b'957176' b'5736' b'7436'
 b'11664' b'62860' b'21336' b'9408' b'12580' b'949668' b'168' b'5116'
 b'22916' b'3920' b'16264' b'4104' b'184120' b'12556' b'64888' b'67508'
 b'193816' b'3228' b'42608' b'37916' b'988636' b'47852' b'5388' b'405768'
 b'577092' b'5236' b'3600' b'108' b'83872' b'95320' b'71440' b'540040'
 b'489120' b'1456' b'66332' b'2848' b'961820' b'4036' b'98160' b'20880'
 b'110032' b'11924' b'145892' b'65260' b'57024' b'1212' b'8592' b'48600'
 b'4240' b'65836' b'84160' b'17756' b'5704' b'6132' b'36444' b'75696'
 b'6628' b'4248' b'51752' b'10808' b'9504' b'67688' b'10348' b'6664'
 b'488608' b'5944' b'8384' b'10892' b'33276' b'5636' b'908212' b'400992'
 b'7632' b'2912' b'52000' b'51716' b'2296' b'7068' b'180204' b'12544'
 b'916296' b'16652' b'108712' b'7880' b'5476' b'14480' b'205884' b'25696'
 b'43108' b'8300' b'7168' b'9320' b'48608' b'54976' b'43384' b'770864'
 b'4328' b'24784' b'82364' b'962268' b'51448' b'36' b'25784' b'49756'
 b'83460' b'66960' b'2524' b'74436' b'4608' b'1320' b'2152' b'65664'
 b'965604' b'3460' b'3700' b'3260' b'56848' b'496468' b'36912' b'4172'
 b'52672' b'42876' b'121728' b'40864' b'71004' b'3668' b'25108' b'551076'
 b'25128' b'777220' b'5444' b'2212' b'1384' b'64748' b'54980' b'54436'
 b'6792' b'750428' b'2180' b'5984' b'36328' b'9788' b'15652' b'4192'
 b'8080' b'3096' b'1420' b'55332' b'64100' b'443368' b'51840' b'48408'
 b'66304' b'26544' b'12404' b'5240' b'35584' b'44588' b'36824' b'8204'
 b'16600' b'5576' b'966360' b'2460' b'113336' b'828748' b'51348' b'9188'
 b'2696' b'108972' b'53684' b'46988' b'413740' b'679560' b'90296' b'49712'
 b'5004' b'528252' b'9360' b'42612' b'111148' b'739472' b'97408' b'12456'
 b'183240' b'45712' b'51868' b'1328' b'1324' b'2232' b'4176']
Feature: top_4_15_day_non_fresh_product
Tensor: [b'1284' b'2572' b'2624' b'124' b'1356' b'1424' b'31068' b'1232' b'65932'
 b'64888' b'3484' b'5736' b'5344' b'65060' b'64824' b'2412' b'88' b'1452'
 b'537340' b'66476' b'17756' b'1220' b'211816' b'12556' b'40456' b'2192'
 b'300016' b'66460' b'3460' b'4816' b'2492' b'64748' b'5464' b'1560'
 b'565660' b'2608' b'99648' b'54980' b'50876' b'1276' b'65140' b'68484'
 b'7108' b'38164' b'5992' b'3428' b'12324' b'1352' b'3344' b'61448'
 b'1228' b'7984' b'11924' b'122680' b'24' b'63120' b'3744' b'24816'
 b'10896' b'79752' b'1312' b'2860' b'65436' b'2144' b'4148' b'7136'
 b'65172' b'108104' b'9884' b'40412' b'140912' b'3880' b'7152' b'48736'
 b'4708' b'211568' b'453788' b'9040' b'16600' b'57152' b'98044' b'14732'
 b'1240' b'19740' b'NA' b'13860' b'2408' b'4948' b'66348' b'70888'
 b'64088' b'6276' b'1332' b'34664' b'53032' b'19420' b'2496' b'3056'
 b'12176' b'4284' b'450748' b'4648' b'3124' b'914476' b'11804' b'9672'
 b'7528' b'10428' b'313612' b'9308' b'7336' b'834652' b'9456' b'2256'
 b'14584' b'771140' b'4748' b'1436' b'74440' b'544116' b'1256' b'66088'
 b'76364' b'2260' b'4464' b'62080' b'3092' b'5136' b'100292' b'2416'
 b'1360' b'11468' b'12204' b'22308' b'2180' b'2332' b'7424' b'4172'
 b'3824' b'170036' b'57616' b'274296' b'5084' b'1500' b'12656' b'2552'
 b'28840' b'2132' b'4104' b'56' b'14760' b'51788' b'2140' b'2540'
 b'915816' b'40620' b'356280' b'573728' b'65096' b'84720' b'1456' b'5080'
 b'9376' b'16236' b'71428' b'34640' b'28' b'1324' b'12544' b'41524'
 b'8680' b'63016' b'15608' b'562740' b'5132' b'52536' b'10104' b'3200'
 b'464592' b'60856' b'1556' b'496796' b'3276' b'8388' b'756752' b'36444'
 b'6348' b'3144' b'108' b'66760' b'64636' b'2504' b'10488' b'4656'
 b'908208' b'3596' b'2516' b'19172' b'9384' b'41552' b'11424' b'7492'
 b'8500' b'8880' b'588416' b'3468' b'93884' b'3392' b'9956' b'331880'
 b'51504' b'2352' b'65016' b'5116' b'56460' b'48408' b'2704' b'10724'
 b'1184' b'4240' b'3644' b'1212' b'342536' b'52316' b'7980' b'12096'
 b'3060' b'2508' b'9140' b'966360' b'20' b'2848' b'45124' b'1572' b'6292'
 b'10624' b'150100' b'6568' b'38452' b'5228' b'4936' b'1244' b'42084'
 b'2772' b'4564' b'3964' b'7632' b'2868' b'5232' b'8868' b'1516' b'293556'
 b'71484' b'4192' b'8552' b'436864' b'66564' b'4408' b'43196' b'11976'
 b'5616' b'51292' b'3488' b'9504' b'7224' b'53688' b'11024' b'14480'
 b'4364' b'2676' b'61112' b'557344' b'56076' b'955216' b'11220' b'7572'
 b'5248' b'610036' b'10792' b'6820' b'764628' b'68204' b'26508' b'90340'
 b'2732' b'5332' b'965524' b'24980' b'5636' b'51716' b'16544' b'765204'
 b'2908' b'7176' b'24836' b'73540' b'86924' b'2348' b'64056' b'2212'
 b'57116' b'160' b'21152' b'70820' b'74700' b'51660' b'1584' b'5688'
 b'14828' b'68512' b'4380' b'823960' b'44416' b'51484' b'51304' b'3236'
 b'11664' b'2588' b'172' b'51372' b'4036' b'100308' b'6356' b'10036'
 b'3480' b'20180' b'88064' b'44992' b'65428' b'2208' b'57644' b'2512'
 b'16128' b'25132' b'2108' b'3028' b'6156' b'16696' b'82836' b'65012'
 b'762820' b'2188' b'4924' b'41512' b'51424' b'14500' b'587804' b'244148'
 b'5312' b'6212' b'8592' b'6452' b'12012' b'749048' b'4988' b'2900'
 b'8384' b'22476' b'9872' b'48900' b'6664' b'17436' b'955756' b'8920'
 b'2568' b'7668' b'79408' b'28888' b'2440' b'8768' b'54232' b'4196'
 b'8300' b'908236' b'8644' b'54920' b'3600' b'16456' b'65452' b'92284'
 b'2456' b'5508' b'561488' b'44884' b'185024' b'65836' b'12532' b'956556'
 b'66956' b'6132' b'41040' b'51584' b'66952' b'75928' b'95584' b'215712'
 b'759628' b'581988' b'4520' b'79924' b'136' b'11200' b'87020' b'1404'
 b'65664' b'169984' b'16168' b'488608' b'76144' b'36568' b'80948'
 b'121688' b'25128' b'47936' b'7072' b'551012' b'74788' b'1464' b'56624'
 b'2384' b'38056' b'8348' b'4508' b'514072' b'25772' b'32' b'10832'
 b'1328' b'682264' b'786928' b'49180' b'67708' b'7084' b'6668' b'16800'
 b'777268' b'537084' b'23988' b'12456' b'11428' b'55904' b'13632' b'16676'
 b'50668' b'408220' b'24284' b'329244' b'6204' b'2524' b'57148' b'3524'
 b'26808' b'5704' b'48424' b'54988' b'12112' b'42460' b'33276' b'11688'
 b'45204' b'48624' b'78848' b'60944' b'65972' b'3660' b'577232' b'2460'
 b'83740' b'5592' b'70516' b'164' b'3808' b'5056' b'86140' b'66992'
 b'4700' b'81828' b'60436' b'2872' b'10808' b'3668' b'12264' b'2296'
 b'22100' b'4276' b'79384' b'42884' b'946780' b'24788' b'12380' b'73248'
 b'22532' b'31060' b'15920' b'756964' b'430392' b'7532' b'3108' b'2248'
 b'5944' b'10224' b'2148' b'4760' b'21944' b'809012' b'33920' b'16136'
 b'40360' b'84928' b'82364' b'81296' b'77960' b'234900' b'51448' b'67412'
 b'12412' b'48852' b'70648' b'4880' b'9368' b'47464' b'12272' b'87196'
 b'65812' b'731448' b'65488' b'86380' b'7608' b'2484' b'537452' b'97980'
 b'606420' b'454504' b'78032' b'21704' b'108812' b'68' b'91936' b'149236'
 b'5008' b'957504' b'17452' b'66684' b'4328' b'68500' b'32836' b'7412'
 b'4696' b'60752' b'1552' b'776856' b'1344' b'485780' b'6364' b'49452'
 b'363512' b'2176' b'71148' b'49708' b'9224']
Feature: top_5_15_day_non_fresh_product
Tensor: [b'2732' b'5056' b'1424' b'1500' b'124' b'63116' b'2456' b'1352' b'2192'
 b'5316' b'6380' b'1368' b'12552' b'2332' b'88' b'22260' b'8500' b'60940'
 b'1600' b'1212' b'36488' b'1452' b'2144' b'965524' b'3596' b'19124'
 b'2488' b'300012' b'6632' b'5344' b'2624' b'2516' b'25128' b'2412'
 b'565772' b'66564' b'4116' b'16536' b'544116' b'23992' b'2304' b'2492'
 b'34580' b'99648' b'41872' b'1284' b'75124' b'30292' b'51348' b'7668'
 b'5636' b'1276' b'66760' b'544756' b'1332' b'2508' b'76220' b'3824'
 b'83740' b'18468' b'2584' b'2704' b'40360' b'445108' b'5616' b'5388'
 b'7736' b'4816' b'2772' b'9792' b'8960' b'3084' b'149492' b'7224'
 b'10036' b'1360' b'682264' b'530580' b'1232' b'2388' b'16524' b'50876'
 b'78052' b'9416' b'36764' b'16072' b'1404' b'NA' b'21108' b'116796'
 b'4908' b'749048' b'28' b'96324' b'1588' b'998260' b'1620' b'12136'
 b'175948' b'81596' b'6348' b'79408' b'2296' b'62448' b'24836' b'94160'
 b'4564' b'2132' b'3056' b'7744' b'1612' b'11884' b'86400' b'2676'
 b'106456' b'3276' b'10092' b'121208' b'949352' b'9472' b'3096' b'51292'
 b'4268' b'559092' b'7228' b'108' b'5024' b'1560' b'1280' b'24816'
 b'64596' b'2776' b'3124' b'2512' b'4328' b'8808' b'83900' b'5812'
 b'829024' b'3236' b'54436' b'16160' b'5704' b'51304' b'76816' b'2540'
 b'153888' b'64228' b'6156' b'65932' b'4196' b'71188' b'450748' b'9544'
 b'999344' b'2800' b'989708' b'211816' b'7716' b'3092' b'66492' b'1356'
 b'4220' b'2696' b'5084' b'68' b'3532' b'3744' b'49532' b'24584' b'64748'
 b'55532' b'2568' b'20' b'4408' b'46264' b'25108' b'61696' b'15980'
 b'17452' b'809012' b'497400' b'51504' b'1220' b'64088' b'16680' b'68196'
 b'62252' b'3668' b'65260' b'49760' b'2860' b'4160' b'1312' b'949800'
 b'8216' b'3488' b'3392' b'3460' b'28840' b'1324' b'12516' b'11696'
 b'7984' b'11756' b'3772' b'562128' b'3060' b'120872' b'27208' b'3100'
 b'4192' b'8212' b'70544' b'11444' b'56624' b'3144' b'1184' b'348820'
 b'8920' b'17896' b'5080' b'24' b'10412' b'36504' b'110196' b'7108'
 b'15960' b'25124' b'5292' b'813516' b'8388' b'51568' b'12324' b'2572'
 b'1556' b'6784' b'2688' b'19740' b'2108' b'595828' b'1188' b'49676'
 b'15920' b'1464' b'4364' b'65436' b'10792' b'4700' b'92264' b'3808'
 b'51444' b'1248' b'65628' b'2352' b'35548' b'2140' b'3332' b'12540'
 b'58356' b'13520' b'6356' b'66040' b'947664' b'203448' b'65252' b'10896'
 b'949872' b'24000' b'3108' b'16456' b'12176' b'565168' b'3344' b'331880'
 b'45440' b'2440' b'3600' b'360296' b'3700' b'116' b'51752' b'5100'
 b'34608' b'749300' b'32' b'2256' b'64004' b'4104' b'25696' b'8556'
 b'597420' b'17756' b'3268' b'12272' b'2588' b'58892' b'2496' b'14188'
 b'10048' b'193816' b'3720' b'68560' b'71340' b'94812' b'71500' b'18504'
 b'22232' b'9884' b'8560' b'1272' b'25748' b'12544' b'780480' b'104'
 b'583820' b'11848' b'1516' b'48276' b'2460' b'3200' b'184120' b'2848'
 b'1320' b'2244' b'4524' b'41524' b'95160' b'65012' b'344412' b'6968'
 b'3880' b'74704' b'25692' b'10428' b'19172' b'78308' b'55064' b'6212'
 b'1420' b'34716' b'2520' b'4520' b'84160' b'4484' b'5136' b'20236' b'76'
 b'4812' b'14760' b'64136' b'65836' b'32936' b'64096' b'2112' b'11836'
 b'60944' b'10072' b'110704' b'113896' b'14524' b'4172' b'14564' b'3480'
 b'22160' b'56804' b'51864' b'66476' b'3444' b'36836' b'65452' b'22320'
 b'277808' b'36824' b'250336' b'357996' b'777220' b'60928' b'6276' b'1456'
 b'56584' b'119344' b'45708' b'1240' b'788508' b'48600' b'219652' b'7084'
 b'70396' b'7608' b'46036' b'5736' b'23988' b'3736' b'784484' b'9200'
 b'6568' b'11656' b'44412' b'64056' b'64468' b'55000' b'13824' b'7720'
 b'12444' b'42604' b'51372' b'9956' b'7980' b'64828' b'5596' b'8408'
 b'60440' b'58884' b'4292' b'96672' b'51448' b'65948' b'65892' b'12832'
 b'730552' b'52004' b'6132' b'300016' b'56924' b'970360' b'67976' b'16224'
 b'45204' b'66348' b'7896' b'2164' b'1416' b'102292' b'464592' b'761392'
 b'51716' b'785236' b'1528' b'6664' b'52492' b'2348' b'5988' b'757252'
 b'82348' b'1304' b'80216' b'1396' b'7892' b'10892' b'784884' b'1460'
 b'823924' b'8452' b'2868' b'2876' b'86348' b'15808' b'36568' b'5332'
 b'67196' b'4784' b'8956' b'533500' b'63996' b'4964' b'12556' b'16544'
 b'65916' b'76868' b'32960' b'7584' b'25772' b'2148' b'6984' b'7424'
 b'12460' b'55908' b'989584' b'16144' b'10196' b'501784' b'3868' b'4380'
 b'8384' b'946776' b'47016' b'476188' b'908208' b'4704' b'66452' b'5924'
 b'66700' b'65688' b'2552' b'82836' b'582000' b'14608' b'293556' b'125324'
 b'63380' b'7492' b'1328' b'3784' b'99288' b'40584' b'5992' b'6452'
 b'75820' b'955768' b'597460' b'538028' b'3464' b'965648' b'54360' b'5244'
 b'4240' b'8080' b'25684' b'86444' b'947460' b'12656' b'488608' b'64000'
 b'76768' b'66108' b'42636' b'93044' b'30816' b'35028' b'1228' b'87016'
 b'777928' b'12636' b'11160' b'9408' b'4480' b'42484' b'14764' b'5676'
 b'19932' b'8064' b'9140' b'68460' b'56592' b'40396' b'98136' b'2864'
 b'17716' b'66016' b'187560' b'421128' b'108296' b'185700' b'74700'
 b'44404' b'60856' b'2292' b'49552' b'11000' b'1548' b'47592' b'11664'
 b'7704' b'22356' b'76920' b'10208' b'500080' b'13884' b'7436' b'14724'
 b'582564' b'5464' b'172188' b'226108' b'51580' b'144' b'5132' b'2248'
 b'11560' b'5872' b'42392' b'295104' b'3544' b'67244' b'54324' b'56600'
 b'8896' b'65488' b'557344' b'2188' b'9908' b'40' b'31068' b'11592'
 b'147232' b'913992' b'2708' b'10480' b'6612' b'184704' b'10684']
Feature: top_1_60_day_non_fresh_product
Tensor: [b'24980' b'124' b'1352' b'1356' b'2456' b'82084' b'65932' b'956856'
 b'53676' b'10104' b'245488' b'2572' b'2192' b'51504' b'2188' b'3440'
 b'66460' b'88' b'65336' b'8500' b'1284' b'392420' b'2496' b'64616'
 b'835436' b'1312' b'1500' b'54436' b'4116' b'40908' b'1424' b'14796'
 b'1184' b'399060' b'99648' b'2704' b'17756' b'5344' b'1560' b'4196'
 b'65428' b'2492' b'91936' b'7488' b'45244' b'40456' b'77996' b'771148'
 b'1228' b'2412' b'24' b'2584' b'40412' b'813520' b'5080' b'66760' b'8592'
 b'2140' b'60396' b'64088' b'12552' b'2732' b'31068' b'28' b'3488' b'1452'
 b'4408' b'1276' b'25128' b'755440' b'7500' b'66320' b'14828' b'7108'
 b'66376' b'57152' b'20' b'455204' b'9904' b'48688' b'7736' b'64252'
 b'66476' b'8388' b'1232' b'8444' b'74700' b'36328' b'8172' b'6348'
 b'92344' b'7224' b'782860' b'70516' b'274296' b'19740' b'10276' b'602856'
 b'234900' b'116452' b'73268' b'3808' b'1272' b'10756' b'3276' b'76'
 b'10808' b'6844' b'613884' b'326180' b'193816' b'51372' b'9956' b'8252'
 b'65904' b'10792' b'14764' b'11160' b'61112' b'65424' b'9384' b'12176'
 b'173052' b'2132' b'3196' b'51292' b'682264' b'750000' b'4816' b'36504'
 b'1332' b'538028' b'7632' b'454264' b'64280' b'4564' b'2688' b'2256'
 b'2776' b'45568' b'7608' b'3668' b'490528' b'51444' b'82464' b'3200'
 b'70292' b'66252' b'84652' b'2416' b'51448' b'5704' b'488608' b'5240'
 b'66564' b'3476' b'9416' b'87612' b'147824' b'82996' b'502228' b'2556'
 b'10896' b'73244' b'2516' b'14480' b'293556' b'2860' b'64664' b'36568'
 b'955216' b'90296' b'83900' b'25108' b'4016' b'60856' b'908212' b'59608'
 b'746452' b'2460' b'5444' b'3744' b'96600' b'7176' b'14628' b'216276'
 b'65244' b'84372' b'87016' b'4704' b'6612' b'95460' b'68196' b'20000'
 b'5076' b'25132' b'12556' b'24940' b'105900' b'949656' b'750380'
 b'603544' b'48704' b'78672' b'146784' b'65836' b'11732' b'539436' b'1240'
 b'913728' b'25116' b'908208' b'41872' b'77908' b'4160' b'48736' b'300016'
 b'28376' b'581988' b'14524' b'64056' b'48900' b'16696' b'8384' b'68392'
 b'13824' b'2568' b'365544' b'111260' b'89136' b'2452' b'25136' b'52004'
 b'588196' b'2508' b'16116' b'9884' b'3484' b'83740' b'3720' b'501784'
 b'64824' b'76588' b'215712' b'540040' b'2540' b'4192' b'6212' b'91720'
 b'110032' b'11924' b'404856' b'1456' b'1360' b'16456' b'60940' b'233732'
 b'71428' b'11944' b'442208' b'2112' b'6664' b'6156' b'142452' b'66148'
 b'3144' b'7984' b'144768' b'24836' b'598956' b'567196' b'32' b'5688'
 b'959932' b'5616' b'51556' b'12544' b'10036' b'16748' b'66348' b'3028'
 b'12184' b'66796' b'11560' b'17596' b'91696' b'2144' b'3344' b'51716'
 b'597344' b'955168' b'6568' b'11848' b'538184' b'49756' b'62916' b'4700'
 b'1304' b'746308' b'65664' b'78052' b'7492' b'92164' b'966464' b'60444'
 b'12380' b'108' b'67244' b'9544' b'77936' b'18948' b'4948' b'2208'
 b'76396' b'5324' b'85348' b'24816' b'12056' b'10028' b'586936' b'121212'
 b'7712' b'2248' b'574696' b'5404' b'7572' b'982568' b'65696' b'444016'
 b'16' b'761164' b'33276' b'6452' b'2280' b'6364' b'65812' b'56024'
 b'65488' b'583488' b'6072' b'12540' b'9040' b'96944' b'1380' b'2264'
 b'83596' b'64112' b'60904' b'7152' b'3516' b'3828' b'448748' b'782776'
 b'55156' b'75788' b'49448' b'4172' b'331880' b'4560' b'97408' b'183240'
 b'3736' b'65288' b'306644' b'55240' b'98496']
Feature: top_2_60_day_non_fresh_product
Tensor: [b'24984' b'2572' b'65436' b'1352' b'1228' b'2492' b'508720' b'48736'
 b'2188' b'64632' b'2144' b'59624' b'1500' b'5344' b'1312' b'64824'
 b'52004' b'66564' b'70516' b'94472' b'1356' b'557064' b'36488' b'57152'
 b'1424' b'2488' b'88' b'9140' b'909192' b'7712' b'6668' b'12556' b'81596'
 b'65428' b'11200' b'54524' b'455536' b'65140' b'25128' b'10756' b'3668'
 b'66460' b'14796' b'14756' b'8888' b'24836' b'80020' b'4240' b'28'
 b'590676' b'300012' b'65812' b'4564' b'97792' b'63120' b'1560' b'24816'
 b'142952' b'5988' b'65444' b'945984' b'7736' b'60928' b'6664' b'8500'
 b'3056' b'67216' b'124' b'2280' b'5240' b'64596' b'73268' b'530580'
 b'1232' b'9040' b'2688' b'83900' b'2192' b'16800' b'565672' b'3200'
 b'538028' b'1284' b'8444' b'65016' b'5228' b'78180' b'12176' b'1452'
 b'809012' b'2132' b'64616' b'27072' b'2456' b'80024' b'914476' b'67328'
 b'76' b'6612' b'51740' b'118652' b'10092' b'75352' b'949352' b'2352'
 b'24' b'12456' b'82836' b'6364' b'7152' b'51504' b'44480' b'917780'
 b'1276' b'65932' b'762880' b'2520' b'908208' b'2440' b'102400' b'10296'
 b'300016' b'51292' b'8388' b'8104' b'4192' b'11224' b'66476' b'965524'
 b'2556' b'452164' b'10808' b'7668' b'989584' b'73276' b'738512' b'6032'
 b'16676' b'11084' b'10792' b'3144' b'2540' b'32920' b'1324' b'65096'
 b'4572' b'73244' b'16236' b'5688' b'22320' b'83872' b'14628' b'66760'
 b'9416' b'5736' b'45644' b'8592' b'14524' b'603544' b'3460' b'5184'
 b'76404' b'139872' b'2508' b'5080' b'4656' b'10036' b'6356' b'49756'
 b'64088' b'1368' b'4816' b'455204' b'25716' b'6348' b'151936' b'56'
 b'183996' b'91936' b'4948' b'454264' b'2632' b'2460' b'6452' b'65260'
 b'6132' b'67028' b'2584' b'66376' b'41864' b'76200' b'9956' b'2412'
 b'102272' b'61112' b'449588' b'5664' b'5084' b'6352' b'908236' b'36568'
 b'2140' b'12540' b'71500' b'20' b'957420' b'54584' b'1184' b'3196'
 b'4704' b'2304' b'3124' b'16456' b'41872' b'11940' b'3744' b'4408'
 b'68028' b'84372' b'3236' b'65836' b'119632' b'2256' b'51672' b'65708'
 b'31116' b'36312' b'309828' b'12600' b'25108' b'2512' b'160' b'24988'
 b'11632' b'5312' b'10992' b'454504' b'11924' b'91280' b'24000' b'173052'
 b'565772' b'8216' b'785820' b'22160' b'5576' b'41524' b'95160' b'67552'
 b'1512' b'153472' b'5704' b'11560' b'168' b'80536' b'54988' b'71804'
 b'5616' b'64952' b'63380' b'22252' b'84160' b'2676' b'823960' b'11848'
 b'64228' b'555808' b'37684' b'83740' b'34380' b'64280' b'2704' b'49664'
 b'60444' b'100308' b'2516' b'74700' b'10104' b'16600' b'7224' b'108'
 b'1244' b'8252' b'4196' b'957296' b'11708' b'68196' b'45080' b'82604'
 b'966160' b'962964' b'444016' b'561804' b'7492' b'10424' b'12436'
 b'784484' b'7108' b'44412' b'592792' b'80344' b'955756' b'92232'
 b'404856' b'988072' b'3276' b'9376' b'54920' b'17756' b'3736' b'1328'
 b'766544' b'4812' b'66956' b'67976' b'2568' b'2504' b'33276' b'7984'
 b'4328' b'776524' b'36504' b'66332' b'51580' b'4148' b'45796' b'80656'
 b'92344' b'3468' b'989184' b'5636' b'57024' b'12532' b'5508' b'100664'
 b'8960' b'54976' b'89560' b'4688' b'108140' b'9408' b'5444' b'443584'
 b'10896' b'3808' b'970944' b'10892' b'579468' b'6568' b'1248' b'24792'
 b'36824' b'45440' b'964104' b'2296' b'16144' b'6156' b'8384' b'68460'
 b'10428' b'4436' b'49552' b'3324' b'5232' b'80460' b'4668' b'11488'
 b'85456' b'744292' b'51372' b'147572' b'51448' b'5056' b'538596' b'36444'
 b'7880' b'583488' b'5920' b'64096' b'965600' b'59580' b'771140' b'110056'
 b'52672' b'76768' b'18504' b'93044' b'140912' b'71004' b'776584' b'32756'
 b'1212' b'286488' b'25132' b'79380' b'2732' b'41516' b'11160' b'272088'
 b'2180' b'67364' b'42600' b'455356' b'36328' b'28352' b'968940' b'30696'
 b'64664' b'829024' b'40360' b'181092' b'1572' b'8768' b'203036' b'757168'
 b'2860' b'52724' b'12360' b'55172' b'71128' b'87020' b'3428' b'76920'
 b'5104' b'966360' b'25116' b'582564' b'749048' b'32764' b'97980'
 b'606420' b'1548' b'1304' b'737736' b'2288' b'6276' b'683160' b'75256'
 b'9888' b'4956' b'51444' b'65904' b'5672' b'234984' b'68500' b'48664'
 b'362508' b'36528' b'6224' b'4104' b'49452' b'3868' b'41584' b'105704'
 b'77100' b'452160' b'2244']
Feature: top_3_60_day_non_fresh_product
Tensor: [b'8676' b'1284' b'65452' b'119632' b'1356' b'2624' b'968504' b'8180'
 b'2572' b'5844' b'51504' b'64888' b'70312' b'10756' b'609960' b'2412'
 b'1500' b'8500' b'1232' b'7152' b'65444' b'62732' b'7668' b'17756'
 b'2144' b'1244' b'12556' b'2732' b'28360' b'2488' b'1424' b'244148'
 b'1352' b'5464' b'12044' b'11424' b'66564' b'10208' b'1276' b'234900'
 b'2132' b'2192' b'749048' b'2492' b'7108' b'48688' b'3056' b'1228' b'88'
 b'14764' b'124' b'24' b'36528' b'6668' b'108104' b'2280' b'3464' b'70516'
 b'1560' b'31112' b'1184' b'4816' b'41872' b'60944' b'100244' b'2860'
 b'3720' b'66460' b'3880' b'48736' b'1516' b'10092' b'86780' b'2296'
 b'52004' b'10104' b'2352' b'10956' b'966464' b'982392' b'490528' b'51448'
 b'51784' b'404856' b'70784' b'6276' b'87036' b'64596' b'34664' b'11220'
 b'3744' b'6212' b'2188' b'40' b'1452' b'65052' b'956856' b'8756' b'52652'
 b'5872' b'73088' b'36584' b'57152' b'1312' b'60904' b'2456' b'234984'
 b'65096' b'14808' b'6348' b'3200' b'559092' b'51292' b'14588' b'300012'
 b'64636' b'57084' b'10808' b'56160' b'59580' b'19172' b'1240' b'2608'
 b'75152' b'2508' b'42424' b'6156' b'80460' b'44480' b'66108' b'749928'
 b'81684' b'2520' b'62252' b'2332' b'753992' b'37748' b'12136' b'6564'
 b'25108' b'14628' b'3144' b'344412' b'51444' b'51372' b'1220' b'2552'
 b'3092' b'7136' b'160' b'34580' b'67692' b'66476' b'399060' b'71132'
 b'309828' b'2704' b'3484' b'14524' b'24816' b'17452' b'70444' b'12176'
 b'135372' b'4564' b'277808' b'300016' b'1568' b'49712' b'610360' b'5080'
 b'771140' b'49684' b'9040' b'2140' b'112988' b'26352' b'73276' b'258728'
 b'949352' b'60856' b'2256' b'1252' b'12516' b'11944' b'16708' b'4780'
 b'5616' b'7492' b'8408' b'68560' b'9628' b'1344' b'71500' b'7424'
 b'964960' b'3808' b'76808' b'105632' b'67244' b'5228' b'66492' b'191112'
 b'761164' b'4196' b'913772' b'36444' b'3608' b'67216' b'958324' b'8412'
 b'12324' b'1456' b'8768' b'2452' b'84160' b'68304' b'5104' b'15920'
 b'6352' b'5348' b'68276' b'6568' b'45528' b'28' b'7880' b'89688'
 b'682264' b'24912' b'5672' b'12552' b'51752' b'20808' b'2588' b'4408'
 b'181936' b'4704' b'97792' b'906288' b'3596' b'25128' b'84020' b'66568'
 b'90236' b'557064' b'71864' b'331880' b'328828' b'86420' b'447028'
 b'75124' b'5344' b'6132' b'51620' b'227660' b'115876' b'64088' b'596044'
 b'2512' b'597420' b'36852' b'36504' b'199800' b'9504' b'8556' b'11664'
 b'32772' b'33412' b'49760' b'3480' b'3816' b'442416' b'64952' b'48304'
 b'65812' b'780480' b'10896' b'52492' b'33044' b'782860' b'7584' b'16536'
 b'45612' b'4936' b'9956' b'766024' b'11512' b'8064' b'4524' b'10036'
 b'48264' b'74704' b'51660' b'42476' b'11344' b'232832' b'2848' b'51716'
 b'5704' b'6052' b'908244' b'7224' b'1368' b'24940' b'32936' b'20152'
 b'989584' b'11836' b'2388' b'20' b'1740' b'16600' b'3488' b'65428'
 b'22160' b'1756' b'11236' b'57004' b'211980' b'56804' b'8384' b'2208'
 b'3920' b'450356' b'989708' b'91280' b'8388' b'577000' b'2440' b'357996'
 b'77380' b'9544' b'64228' b'3476' b'64280' b'587804' b'557748' b'NA'
 b'957176' b'12096' b'11848' b'55064' b'48412' b'1464' b'3736' b'9408'
 b'967048' b'101384' b'444016' b'912344' b'65968' b'12636' b'3668'
 b'251808' b'12716' b'4112' b'24988' b'682952' b'140004' b'577092' b'5236'
 b'96208' b'501788' b'54464' b'6512' b'776584' b'60396' b'3344' b'785236'
 b'455204' b'83872' b'1404' b'12544' b'908236' b'55256' b'65216' b'71004'
 b'99868' b'7892' b'1304' b'488608' b'25116' b'108' b'47936' b'7736'
 b'770056' b'65696' b'65828' b'5444' b'11432' b'6548' b'91128' b'110196'
 b'36568' b'2416' b'9904' b'908208' b'56996' b'19356' b'786928' b'5944'
 b'117412' b'4572' b'83132' b'597236' b'5136' b'75656' b'502228' b'54976'
 b'16652' b'65892' b'67364' b'17528' b'75256' b'184192' b'66320' b'28344'
 b'19740' b'8592' b'9056' b'754876' b'48608' b'7072' b'65972' b'3784'
 b'583288' b'744460' b'82364' b'175656' b'12436' b'1556' b'5056' b'2516'
 b'3124' b'7984' b'19192' b'52220' b'586936' b'149840' b'59640' b'7572'
 b'125172' b'51556' b'496468' b'79384' b'2776' b'42912' b'24788' b'63196'
 b'8260' b'30816' b'551076' b'81596' b'36848' b'81908' b'9756' b'499452'
 b'7532' b'613884' b'42444' b'903488' b'59332' b'40396' b'770864' b'2268'
 b'70636' b'3096' b'9376' b'8888' b'70292' b'485780' b'80776' b'11024'
 b'1272' b'5240' b'538184' b'4880' b'67976' b'603544' b'64708' b'36824'
 b'12272' b'86436' b'51416' b'200112' b'411544' b'14732' b'6392' b'957816'
 b'4520' b'12360' b'45796' b'14560' b'5004' b'528252' b'51364' b'36396'
 b'766544' b'49764' b'4948' b'51484' b'42612' b'67704' b'32800' b'12656'
 b'78052' b'1736' b'5584' b'26828' b'913992' b'12676' b'6452' b'76'
 b'1324' b'72060']
Feature: top_4_60_day_non_fresh_product
Tensor: [b'88' b'6212' b'1424' b'1500' b'118652' b'124' b'1352' b'174456'
 b'300016' b'51448' b'41872' b'80536' b'66088' b'12552' b'6664' b'2732'
 b'2508' b'2132' b'65336' b'66564' b'62080' b'14760' b'6364' b'17756'
 b'19124' b'45520' b'66108' b'66460' b'3600' b'1284' b'81096' b'300012'
 b'25108' b'949352' b'67704' b'1356' b'2556' b'99648' b'2412' b'12176'
 b'2192' b'4408' b'63120' b'2416' b'34580' b'1452' b'2704' b'57164'
 b'366352' b'173052' b'6380' b'1312' b'61448' b'5312' b'1560' b'1332'
 b'12136' b'173436' b'11512' b'5080' b'78384' b'41864' b'71128' b'2144'
 b'2460' b'60856' b'9676' b'90404' b'5228' b'444016' b'51504' b'84652'
 b'79040' b'91384' b'36824' b'11472' b'293556' b'682264' b'119880'
 b'453788' b'60944' b'49552' b'14628' b'503952' b'64616' b'11236' b'1208'
 b'51412' b'7108' b'4816' b'1472' b'749048' b'65896' b'2304' b'331880'
 b'5240' b'968576' b'65824' b'7152' b'3744' b'3056' b'61696' b'1596'
 b'2492' b'450748' b'51304' b'482208' b'64596' b'5332' b'1276' b'9672'
 b'12344' b'6844' b'530580' b'20' b'3200' b'598592' b'82836' b'2848'
 b'67412' b'9456' b'12260' b'1344' b'908208' b'583488' b'2608' b'10892'
 b'30888' b'66476' b'31116' b'213108' b'16600' b'1304' b'36488' b'5344'
 b'113192' b'1228' b'3276' b'5736' b'10104' b'41780' b'2572' b'51736'
 b'1232' b'9904' b'110032' b'36504' b'108104' b'4564' b'51672' b'56472'
 b'65932' b'7500' b'3464' b'83272' b'3392' b'999344' b'70428' b'7104'
 b'7224' b'10036' b'140036' b'52044' b'611000' b'16272' b'44392' b'76'
 b'5104' b'174788' b'78436' b'91936' b'71440' b'40620' b'6156' b'1456'
 b'987808' b'68236' b'8388' b'67976' b'28' b'1324' b'8500' b'41524'
 b'60840' b'3532' b'3476' b'14732' b'49732' b'56136' b'3808' b'4160'
 b'464592' b'2552' b'3144' b'104968' b'108' b'2568' b'71452' b'65016'
 b'54436' b'6348' b'2180' b'160' b'42424' b'57152' b'10428' b'8216'
 b'6132' b'66320' b'2456' b'196688' b'68572' b'49664' b'61064' b'7492'
 b'8880' b'80068' b'45440' b'3920' b'8556' b'404832' b'5872' b'65444'
 b'375516' b'12656' b'68276' b'7712' b'16800' b'6568' b'83872' b'3564'
 b'3596' b'1184' b'68216' b'64228' b'48664' b'7508' b'36444' b'7560'
 b'10792' b'244148' b'NA' b'761168' b'150100' b'65424' b'10092' b'64088'
 b'811500' b'73244' b'948284' b'95648' b'50708' b'65492' b'780244'
 b'81892' b'57496' b'949792' b'8896' b'66796' b'771296' b'3736' b'4192'
 b'9956' b'454264' b'1432' b'43196' b'35228' b'1420' b'6352' b'4700'
 b'5136' b'76588' b'48412' b'5236' b'4040' b'2208' b'168' b'120' b'22100'
 b'4316' b'44092' b'67364' b'7668' b'9544' b'61112' b'65436' b'2512'
 b'234900' b'27300' b'24' b'80460' b'357704' b'14524' b'5464' b'440168'
 b'11488' b'48276' b'16668' b'60440' b'16544' b'18448' b'64664' b'109364'
 b'467604' b'64136' b'746024' b'908244' b'26404' b'74704' b'21152' b'32'
 b'12556' b'78308' b'66568' b'5688' b'65428' b'92164' b'597840' b'36820'
 b'66448' b'43528' b'44416' b'51484' b'54976' b'11848' b'65216' b'71428'
 b'124800' b'3236' b'3488' b'75124' b'63400' b'9040' b'1748' b'25116'
 b'681956' b'908236' b'3480' b'146784' b'45244' b'164' b'60940' b'12636'
 b'3468' b'36568' b'16696' b'51372' b'16176' b'60928' b'11664' b'52004'
 b'10636' b'14532' b'65816' b'14500' b'904524' b'51716' b'2440' b'84160'
 b'83740' b'50436' b'766024' b'22252' b'950768' b'64824' b'588048'
 b'48704' b'175644' b'1212' b'79408' b'5404' b'736060' b'96216' b'51292'
 b'184636' b'8644' b'78544' b'7884' b'36848' b'16536' b'67508' b'2352'
 b'3904' b'1404' b'26804' b'41040' b'2516' b'4328' b'82996' b'3668'
 b'190232' b'92668' b'489120' b'8720' b'7616' b'99288' b'502584' b'10384'
 b'103364' b'77868' b'16168' b'70516' b'76144' b'152900' b'83900' b'25128'
 b'8064' b'344412' b'8452' b'19740' b'48680' b'9408' b'1464' b'19172'
 b'611596' b'8252' b'2236' b'908212' b'51752' b'514072' b'7080' b'60272'
 b'65812' b'488608' b'75256' b'65916' b'11468' b'24916' b'21300' b'51436'
 b'4380' b'8384' b'68468' b'8540' b'15920' b'51444' b'131140' b'55336'
 b'6204' b'405768' b'1256' b'66452' b'31068' b'5444' b'48624' b'7716'
 b'530380' b'182520' b'33108' b'903488' b'25784' b'66256' b'86140'
 b'771140' b'1320' b'965648' b'10808' b'2860' b'7228' b'141012' b'7980'
 b'86444' b'309828' b'1460' b'6968' b'595828' b'4936' b'24836' b'9376'
 b'22188' b'41496' b'2140' b'430812' b'7876' b'99880' b'756964' b'373576'
 b'4948' b'2248' b'28660' b'565660' b'3124' b'1220' b'9416' b'5508'
 b'809012' b'50876' b'6392' b'2864' b'379780' b'1496' b'97408' b'12620'
 b'64100' b'443368' b'64636' b'2296' b'573728' b'6240' b'1328' b'684088'
 b'11344' b'117400' b'48936' b'1308' b'4520' b'279408' b'914476' b'2264'
 b'66532' b'753992' b'36836' b'24932' b'326180' b'9872' b'1548' b'226108'
 b'64096' b'17392' b'42912' b'2776' b'52220' b'7176' b'5008' b'957504'
 b'10832' b'5476' b'45364' b'56540' b'67688' b'103080' b'79644' b'819108'
 b'533496' b'3720' b'6612' b'4908' b'2532' b'12672' b'150352' b'749112']
Feature: top_5_60_day_non_fresh_product
Tensor: [b'1284' b'12092' b'1500' b'64616' b'31068' b'1424' b'777928' b'757168'
 b'2440' b'51504' b'54988' b'945672' b'65444' b'736296' b'193904' b'5240'
 b'9740' b'1356' b'65932' b'1220' b'47936' b'2624' b'1212' b'124' b'1452'
 b'949352' b'74704' b'3596' b'68204' b'300016' b'565168' b'16456' b'60904'
 b'2492' b'6568' b'1232' b'68276' b'1572' b'565660' b'80460' b'2608'
 b'2264' b'544116' b'64088' b'455204' b'87016' b'83740' b'19740' b'105744'
 b'41872' b'9904' b'17756' b'3428' b'1456' b'88' b'12436' b'37752'
 b'65016' b'2556' b'2256' b'113192' b'1228' b'7224' b'4196' b'34384'
 b'97792' b'8500' b'152556' b'65436' b'66108' b'461164' b'51292' b'1352'
 b'65828' b'5596' b'7152' b'2352' b'65140' b'79160' b'771140' b'64824'
 b'56584' b'8216' b'6348' b'482992' b'2388' b'5812' b'50876' b'70364'
 b'2572' b'98044' b'12032' b'10036' b'125284' b'22252' b'400124' b'566300'
 b'78000' b'2704' b'9344' b'12136' b'82864' b'65496' b'66452' b'3668'
 b'5508' b'6156' b'1620' b'2848' b'66312' b'946780' b'1568' b'443832'
 b'11848' b'92232' b'914476' b'2132' b'2520' b'64704' b'2412' b'7720'
 b'70624' b'6448' b'908236' b'3488' b'1312' b'956972' b'84720' b'44796'
 b'80344' b'5624' b'2512' b'2516' b'54984' b'49664' b'5576' b'16160'
 b'5444' b'374376' b'293556' b'3744' b'2540' b'51348' b'117136' b'76224'
 b'81248' b'2140' b'8672' b'104796' b'9544' b'1276' b'3144' b'12656'
 b'76564' b'184120' b'8464' b'25692' b'10428' b'150304' b'171184' b'55380'
 b'10412' b'765808' b'599032' b'52048' b'2304' b'24584' b'64748' b'908244'
 b'1332' b'24788' b'193816' b'43260' b'8384' b'57152' b'595936' b'4948'
 b'3476' b'14584' b'3464' b'71428' b'50552' b'9320' b'583488' b'6276'
 b'2456' b'767916' b'65248' b'66376' b'117440' b'63016' b'28' b'65836'
 b'60856' b'10908' b'27220' b'7816' b'78876' b'4408' b'3124' b'3920'
 b'16168' b'2192' b'76764' b'44412' b'65420' b'5736' b'2504' b'3408'
 b'48936' b'105900' b'1184' b'11444' b'66332' b'65336' b'5616' b'7220'
 b'2568' b'3604' b'5080' b'12400' b'70516' b'51372' b'24' b'60388' b'3824'
 b'17724' b'6132' b'207580' b'6072' b'581856' b'36348' b'8388' b'2688'
 b'110204' b'12176' b'170588' b'2188' b'32936' b'2392' b'20828' b'784180'
 b'66040' b'1528' b'19928' b'66564' b'4800' b'45612' b'5236' b'NA' b'7492'
 b'103984' b'9956' b'50444' b'81596' b'566344' b'65096' b'7216' b'2148'
 b'116456' b'1244' b'32' b'9676' b'185588' b'4564' b'184704' b'66320'
 b'88408' b'3060' b'9504' b'1328' b'11656' b'3200' b'66460' b'105716'
 b'60444' b'71484' b'51752' b'5664' b'955608' b'55476' b'1404' b'2332'
 b'8556' b'54976' b'85388' b'57116' b'785236' b'4508' b'40920' b'1560'
 b'160' b'10092' b'8552' b'20' b'67976' b'7736' b'244148' b'3720' b'3424'
 b'82996' b'42488' b'36848' b'7572' b'3444' b'1280' b'7668' b'70728'
 b'44692' b'557344' b'33460' b'2732' b'51444' b'7108' b'11560' b'77096'
 b'537452' b'33108' b'64252' b'1368' b'277808' b'60940' b'489216' b'2280'
 b'557064' b'64096' b'6212' b'482220' b'108940' b'9408' b'61064' b'564856'
 b'3460' b'3344' b'24836' b'813516' b'45652' b'51304' b'3808' b'2672'
 b'78124' b'7880' b'65896' b'2108' b'16536' b'7704' b'908208' b'300012'
 b'205884' b'45368' b'56088' b'65816' b'51320' b'84156' b'1200' b'16176'
 b'14524' b'82836' b'84652' b'111260' b'989708' b'76' b'1240' b'11168'
 b'466720' b'21676' b'7716' b'344412' b'3880' b'788508' b'31116' b'52460'
 b'70396' b'36312' b'65524' b'3056' b'737736' b'91280' b'85036' b'115332'
 b'3468' b'84016' b'25128' b'83048' b'4816' b'24940' b'813504' b'558208'
 b'56624' b'84' b'4104' b'10184' b'57620' b'12544' b'247004' b'72'
 b'51448' b'56076' b'452164' b'1552' b'4172' b'7336' b'19512' b'406252'
 b'12204' b'36568' b'45204' b'51584' b'464592' b'108' b'51784' b'71440'
 b'761392' b'7632' b'2508' b'10808' b'76388' b'19172' b'5228' b'12848'
 b'66568' b'3600' b'1188' b'601492' b'42484' b'20880' b'79340' b'965524'
 b'80216' b'19188' b'91936' b'48600' b'113520' b'16224' b'923888'
 b'505332' b'112776' b'88112' b'5332' b'36712' b'614040' b'123432'
 b'16236' b'1272' b'73088' b'55048' b'93620' b'66476' b'682264' b'2696'
 b'11732' b'32960' b'3516' b'65832' b'3828' b'3564' b'56344' b'26068'
 b'11836' b'93044' b'16600' b'30724' b'501784' b'16004' b'2208' b'84976'
 b'214972' b'65488' b'42056' b'2860' b'1464' b'60396' b'66684' b'66348'
 b'94992' b'7168' b'2552' b'501788' b'33276' b'64280' b'4148' b'5388'
 b'102380' b'4328' b'43880' b'43612' b'99288' b'4572' b'4316' b'64136'
 b'6452' b'17448' b'82368' b'2588' b'965604' b'11208' b'9868' b'4380'
 b'12676' b'48264' b'95916' b'56848' b'14732' b'286488' b'598592' b'73408'
 b'51484' b'7888' b'25116' b'66680' b'51864' b'5672' b'113544' b'12260'
 b'430392' b'55620' b'51180' b'2296' b'14764' b'6700' b'66088' b'811132'
 b'5984' b'11156' b'218024' b'102692' b'7084' b'3700' b'592792' b'2524'
 b'2112' b'9804' b'34572' b'82364' b'2728' b'41516' b'67412' b'50872'
 b'1440' b'6816' b'4700' b'766544' b'724144' b'14804' b'414468' b'10104'
 b'1252' b'2144' b'66648' b'273356' b'1304' b'82192' b'186664' b'35688'
 b'1460' b'2176' b'41532' b'51580' b'55064' b'757252' b'48556' b'75788'
 b'6524' b'12056' b'15804' b'7712' b'2260' b'3480' b'59624' b'153888'
 b'3220' b'25108' b'2584' b'196' b'16072' b'36488' b'7616' b'51616'
 b'4524' b'16676' b'40456' b'4160' b'51876' b'6848' b'8920']
Feature: top_1_90_day_non_fresh_product
Tensor: [b'24980' b'124' b'1352' b'1356' b'2456' b'48736' b'2188' b'64632' b'6380'
 b'10104' b'245488' b'2572' b'52004' b'51504' b'7152' b'66460' b'66564'
 b'65336' b'8500' b'1284' b'97792' b'2496' b'64616' b'835436' b'1312'
 b'1500' b'81596' b'65428' b'40908' b'88' b'1424' b'14796' b'1184'
 b'399060' b'99648' b'2704' b'17756' b'5344' b'1560' b'4196' b'2492'
 b'91936' b'7488' b'45244' b'77996' b'771148' b'1228' b'2412' b'24'
 b'40412' b'813520' b'5080' b'10756' b'8592' b'2140' b'60396' b'64088'
 b'14628' b'2732' b'31068' b'28' b'3488' b'1452' b'4408' b'1276' b'25128'
 b'755440' b'7500' b'66320' b'4816' b'14828' b'7108' b'66376' b'57152'
 b'20' b'2192' b'914476' b'48688' b'7736' b'118652' b'8388' b'1232'
 b'8444' b'74700' b'36328' b'8172' b'6348' b'102400' b'16412' b'76224'
 b'70516' b'274296' b'19740' b'51444' b'602856' b'16676' b'73268' b'3808'
 b'10792' b'595936' b'908244' b'3276' b'4812' b'49712' b'67976' b'613884'
 b'326180' b'66760' b'51372' b'3668' b'557064' b'8252' b'65904' b'7224'
 b'603544' b'5184' b'76404' b'14764' b'2508' b'61112' b'65424' b'9384'
 b'12176' b'173052' b'2132' b'3196' b'51292' b'11848' b'750000' b'36504'
 b'1332' b'538028' b'2460' b'2584' b'64280' b'4564' b'2688' b'182520'
 b'2256' b'2776' b'5104' b'45568' b'7608' b'65444' b'490528' b'82464'
 b'44544' b'3200' b'84652' b'956856' b'2416' b'10808' b'51448' b'5704'
 b'488608' b'63996' b'9416' b'87612' b'147824' b'82996' b'65932' b'12552'
 b'502228' b'2556' b'10896' b'73244' b'25108' b'2516' b'14480' b'293556'
 b'2860' b'64664' b'2512' b'955216' b'3480' b'83900' b'4016' b'24912'
 b'908212' b'59608' b'48276' b'5444' b'96600' b'7176' b'908208' b'153472'
 b'84372' b'87016' b'4704' b'6612' b'36568' b'95460' b'68196' b'3744'
 b'737736' b'823960' b'83740' b'12556' b'60856' b'16600' b'949656'
 b'56088' b'25132' b'48704' b'78672' b'65836' b'12540' b'539436' b'966160'
 b'957504' b'41872' b'77908' b'7492' b'10424' b'300016' b'28376' b'581988'
 b'64056' b'48900' b'16696' b'9956' b'8384' b'92232' b'365544' b'89136'
 b'2452' b'5228' b'140004' b'588196' b'16116' b'9884' b'1420' b'3720'
 b'501784' b'64824' b'215712' b'540040' b'1240' b'2540' b'83872' b'6212'
 b'45796' b'110032' b'11924' b'92344' b'11760' b'1360' b'60940' b'233732'
 b'5508' b'71428' b'5332' b'331880' b'442208' b'2112' b'6664' b'6156'
 b'142452' b'66148' b'514072' b'3144' b'7984' b'144768' b'24836' b'537452'
 b'68468' b'16144' b'51556' b'12544' b'51320' b'16748' b'66348' b'3028'
 b'66796' b'24816' b'2144' b'3344' b'51716' b'597344' b'6568' b'81296'
 b'49756' b'62916' b'4700' b'1304' b'746308' b'2520' b'2588' b'78052'
 b'4948' b'92164' b'966464' b'60444' b'4160' b'108' b'17596' b'67244'
 b'9544' b'77936' b'18948' b'76396' b'85348' b'12056' b'65016' b'121212'
 b'3476' b'7712' b'2248' b'574696' b'5404' b'181092' b'65696' b'444016'
 b'16' b'761164' b'33276' b'6452' b'36512' b'2280' b'6364' b'452164'
 b'65488' b'54988' b'454264' b'583488' b'6072' b'97980' b'9040' b'3736'
 b'36444' b'6276' b'83596' b'64112' b'60904' b'12360' b'3516' b'5476'
 b'782776' b'234984' b'75788' b'49448' b'362508' b'20984' b'4560' b'97408'
 b'183240' b'65288' b'306644' b'51868' b'12672' b'55240' b'56460']
Feature: top_2_90_day_non_fresh_product
Tensor: [b'24984' b'2572' b'65436' b'1352' b'1228' b'124' b'508720' b'8180'
 b'65932' b'956856' b'2144' b'6816' b'1500' b'5344' b'1312' b'64824'
 b'2192' b'66564' b'70516' b'94472' b'1356' b'11488' b'88' b'57152'
 b'1424' b'2488' b'2732' b'64888' b'244148' b'51504' b'12556' b'11424'
 b'54436' b'4116' b'11200' b'54524' b'4408' b'10756' b'3668' b'2492'
 b'66460' b'14796' b'14756' b'7108' b'8888' b'24836' b'19420' b'4240'
 b'28' b'66376' b'300012' b'65812' b'1284' b'12136' b'24' b'63120' b'6668'
 b'1184' b'142952' b'78384' b'40456' b'945984' b'7736' b'6664' b'444016'
 b'2860' b'2584' b'67216' b'3880' b'5240' b'64596' b'66760' b'73268'
 b'530580' b'1232' b'9040' b'2688' b'84720' b'503952' b'2352' b'538028'
 b'8444' b'51784' b'404856' b'5228' b'6276' b'12176' b'1452' b'65824'
 b'3744' b'5616' b'2132' b'64616' b'65140' b'65052' b'494860' b'80024'
 b'455204' b'9904' b'73088' b'76716' b'2520' b'6612' b'51740' b'64252'
 b'66476' b'10092' b'908236' b'8500' b'12456' b'82836' b'10808' b'6568'
 b'1276' b'44480' b'917780' b'9408' b'2440' b'25128' b'110032' b'51292'
 b'51672' b'8388' b'37748' b'11224' b'965524' b'2556' b'452164' b'7668'
 b'989584' b'7224' b'64088' b'495964' b'6156' b'116452' b'9812' b'1272'
 b'2704' b'3144' b'70444' b'32920' b'65096' b'10636' b'73244' b'139848'
 b'5688' b'71004' b'83872' b'455536' b'14628' b'193816' b'9416' b'63016'
 b'5056' b'8592' b'9956' b'14524' b'60856' b'10792' b'3460' b'67016'
 b'1560' b'11160' b'4656' b'10036' b'49756' b'49664' b'4816' b'25716'
 b'6348' b'682264' b'300016' b'67244' b'56' b'454264' b'36444' b'6452'
 b'41872' b'67028' b'12204' b'41864' b'2412' b'66040' b'19928' b'6352'
 b'5664' b'12552' b'5084' b'7492' b'36568' b'24912' b'2140' b'3200'
 b'70292' b'66252' b'20' b'16600' b'54584' b'3196' b'4704' b'184704'
 b'2256' b'3124' b'14480' b'68028' b'84372' b'3236' b'908208' b'3476'
 b'35228' b'119632' b'4508' b'65708' b'31116' b'213108' b'309828' b'12600'
 b'67364' b'5736' b'160' b'11632' b'5080' b'65444' b'90296' b'27300'
 b'60192' b'48304' b'565772' b'44692' b'2540' b'31120' b'746452' b'64228'
 b'60440' b'41524' b'95160' b'76364' b'216276' b'65244' b'2516' b'5704'
 b'68572' b'80536' b'48264' b'54988' b'71804' b'2508' b'64952' b'2460'
 b'22252' b'84160' b'5076' b'44416' b'11848' b'555808' b'37684' b'25132'
 b'34380' b'17196' b'24940' b'60444' b'100308' b'6356' b'4564' b'22160'
 b'74700' b'10104' b'25116' b'2208' b'450356' b'1244' b'8172' b'31112'
 b'4196' b'3056' b'146784' b'957448' b'65896' b'1368' b'11708' b'68196'
 b'51716' b'45080' b'82604' b'913728' b'962964' b'4160' b'55064' b'12436'
 b'7608' b'175644' b'80344' b'955756' b'25108' b'3468' b'988072' b'3276'
 b'771140' b'54920' b'83740' b'16536' b'25136' b'100832' b'1404' b'108'
 b'6132' b'2304' b'2568' b'2504' b'17756' b'501788' b'776524' b'36504'
 b'785236' b'66956' b'66332' b'4192' b'4148' b'91720' b'51372' b'98160'
 b'99868' b'8216' b'91936' b'2456' b'12532' b'100664' b'8960' b'54976'
 b'11432' b'60708' b'5444' b'443584' b'67688' b'3808' b'970944' b'8384'
 b'579468' b'3828' b'41032' b'567196' b'5136' b'964104' b'2296' b'501784'
 b'5464' b'51444' b'65836' b'65892' b'4948' b'3324' b'11560' b'66320'
 b'17596' b'1516' b'64280' b'48608' b'4668' b'85456' b'955168' b'51448'
 b'3736' b'7880' b'746316' b'64096' b'65664' b'965600' b'120700' b'59580'
 b'51556' b'32' b'14732' b'52672' b'6212' b'76768' b'12380' b'9376'
 b'32756' b'30816' b'286488' b'5324' b'3596' b'5872' b'586936' b'2180'
 b'52004' b'455356' b'59332' b'50876' b'968940' b'70636' b'64664'
 b'829024' b'40360' b'281424' b'7572' b'1572' b'11024' b'10424' b'12360'
 b'603544' b'3060' b'71128' b'60940' b'76920' b'51320' b'966360' b'582564'
 b'749048' b'51348' b'766544' b'55156' b'1380' b'2264' b'683160' b'4956'
 b'65904' b'83900' b'48664' b'4172' b'67704' b'6224' b'5236' b'3868'
 b'41584' b'12676' b'105704' b'452160' b'14584' b'1324' b'150352' b'98496']
Feature: top_3_90_day_non_fresh_product
Tensor: [b'6348' b'6212' b'65452' b'119632' b'1356' b'2492' b'1352' b'24044'
 b'2572' b'76224' b'41872' b'9396' b'51504' b'70312' b'10756' b'5240'
 b'2412' b'1500' b'65932' b'1232' b'3440' b'65444' b'557064' b'7668'
 b'17756' b'2144' b'949352' b'12556' b'9140' b'66108' b'300012' b'7712'
 b'60904' b'1424' b'25108' b'66564' b'10208' b'1276' b'12176' b'65140'
 b'63120' b'749048' b'2256' b'1284' b'2704' b'57164' b'2488' b'3056'
 b'12436' b'1228' b'590676' b'5312' b'14764' b'8228' b'88' b'4196' b'5080'
 b'97792' b'31112' b'71128' b'1184' b'9676' b'124' b'60928' b'65828'
 b'113404' b'9956' b'66460' b'7152' b'11472' b'8500' b'1516' b'682264'
 b'119880' b'86780' b'7108' b'10428' b'16800' b'5228' b'51660' b'5344'
 b'490528' b'51448' b'28' b'2304' b'78180' b'87036' b'82864' b'4104'
 b'2732' b'2188' b'40' b'81644' b'1452' b'956856' b'482208' b'2192'
 b'52652' b'9672' b'36584' b'76' b'766544' b'234984' b'75352' b'65424'
 b'7224' b'6568' b'51752' b'51292' b'12552' b'84720' b'17916' b'6364'
 b'49664' b'59580' b'2552' b'1240' b'54984' b'6156' b'42424' b'10104'
 b'2520' b'80460' b'44480' b'749928' b'81684' b'1560' b'2456' b'62252'
 b'92344' b'753992' b'7500' b'6452' b'913728' b'9544' b'51444' b'70428'
 b'1220' b'9344' b'10036' b'496084' b'234900' b'2132' b'399060' b'64220'
 b'24812' b'5104' b'174788' b'14524' b'2540' b'9040' b'4564' b'277808'
 b'300016' b'21912' b'771140' b'49684' b'10288' b'60840' b'5736' b'45644'
 b'49732' b'25128' b'73276' b'49760' b'2608' b'60944' b'2568' b'71452'
 b'5616' b'54436' b'16104' b'3144' b'7492' b'4520' b'57152' b'6132'
 b'3200' b'1344' b'83740' b'51648' b'68572' b'90864' b'7424' b'8880'
 b'5444' b'3808' b'76808' b'24' b'151936' b'51372' b'8388' b'183996'
 b'4948' b'41516' b'913772' b'2632' b'68276' b'2556' b'958324' b'12780'
 b'83872' b'2452' b'84160' b'19740' b'4816' b'52004' b'3488' b'102272'
 b'449588' b'45612' b'12324' b'60444' b'7880' b'103980' b'64824' b'5672'
 b'12540' b'71500' b'1528' b'2588' b'4408' b'917948' b'4704' b'9904'
 b'95648' b'32' b'65492' b'16456' b'90236' b'66476' b'328828' b'86420'
 b'771296' b'3736' b'4192' b'34608' b'44984' b'64276' b'5136' b'12532'
 b'5236' b'10828' b'40920' b'11224' b'12136' b'2512' b'24988' b'36568'
 b'65436' b'10992' b'42488' b'91280' b'1404' b'64952' b'65812' b'3824'
 b'41864' b'3744' b'22160' b'7584' b'16544' b'64664' b'537452' b'54044'
 b'1512' b'11512' b'7736' b'8064' b'168' b'91936' b'78308' b'4300'
 b'63380' b'2848' b'2516' b'20000' b'5704' b'6052' b'54976' b'1368'
 b'5688' b'20152' b'124800' b'2352' b'3668' b'2860' b'75124' b'63400'
 b'838576' b'16600' b'65428' b'105900' b'1756' b'11236' b'40476' b'119244'
 b'949832' b'67276' b'2508' b'1200' b'454264' b'48736' b'8252' b'2440'
 b'10636' b'11732' b'14500' b'904524' b'587804' b'NA' b'957176' b'561804'
 b'10808' b'22252' b'64088' b'65524' b'588048' b'44412' b'592792' b'2676'
 b'68392' b'8920' b'36444' b'404856' b'81328' b'66568' b'65968' b'1324'
 b'10896' b'57620' b'12544' b'12716' b'64280' b'452164' b'20' b'2624'
 b'44888' b'577092' b'66956' b'67976' b'3484' b'96208' b'4328' b'76588'
 b'6512' b'776584' b'19172' b'55256' b'65216' b'77868' b'16168' b'112988'
 b'4524' b'51740' b'116388' b'77908' b'488608' b'12580' b'25116' b'47936'
 b'8452' b'770056' b'65696' b'89560' b'11944' b'4688' b'34384' b'9496'
 b'76732' b'108140' b'9408' b'6628' b'908208' b'60940' b'19356' b'786928'
 b'75256' b'60856' b'11468' b'21300' b'83132' b'597236' b'1312' b'24792'
 b'45440' b'603544' b'16676' b'48852' b'16652' b'68460' b'12184' b'1552'
 b'66684' b'2280' b'91696' b'5232' b'8592' b'82836' b'102380' b'65972'
 b'33108' b'82364' b'147572' b'70516' b'15920' b'3124' b'66960' b'19192'
 b'5920' b'965648' b'586936' b'2776' b'149840' b'59640' b'7228' b'7572'
 b'64596' b'110056' b'86444' b'2180' b'24788' b'48952' b'18504' b'93044'
 b'8260' b'1212' b'551076' b'81596' b'81908' b'9756' b'65672' b'914116'
 b'74752' b'613884' b'74704' b'67364' b'42600' b'903488' b'32756' b'36328'
 b'75792' b'2268' b'11432' b'30696' b'12620' b'2728' b'2296' b'982568'
 b'404584' b'36504' b'13776' b'757168' b'52724' b'450340' b'4880' b'32920'
 b'3920' b'87020' b'3428' b'54980' b'411544' b'2416' b'606420' b'1548'
 b'9872' b'57588' b'8616' b'1304' b'957816' b'11560' b'9888' b'7176'
 b'5004' b'528252' b'16512' b'51364' b'2140' b'36396' b'37752' b'68500'
 b'51484' b'2584' b'331880' b'533496' b'12656' b'78052' b'7616' b'1224'
 b'557344' b'26828' b'45620' b'913992' b'400992' b'108']
Feature: top_4_90_day_non_fresh_product
Tensor: [b'88' b'1284' b'1424' b'1500' b'31068' b'2624' b'968504' b'82084'
 b'65444' b'576656' b'51504' b'11684' b'66088' b'12552' b'3596' b'63124'
 b'1312' b'1356' b'8500' b'2132' b'47936' b'65812' b'28' b'62080' b'14760'
 b'1244' b'17756' b'139988' b'909192' b'120828' b'16456' b'7176' b'6568'
 b'300012' b'25128' b'65016' b'2492' b'2412' b'234900' b'455536' b'81596'
 b'2416' b'105744' b'9904' b'66460' b'64664' b'1456' b'124' b'1352'
 b'1560' b'8388' b'66564' b'173436' b'24816' b'9344' b'3124' b'70516'
 b'1276' b'445108' b'31112' b'60856' b'4816' b'41872' b'90404' b'108104'
 b'2352' b'3720' b'79040' b'771140' b'2280' b'48736' b'293556' b'2572'
 b'6204' b'65428' b'12672' b'2296' b'2192' b'64616' b'10104' b'565672'
 b'1208' b'10956' b'400124' b'749048' b'2704' b'70784' b'5240' b'34664'
 b'48756' b'71428' b'5508' b'2452' b'3056' b'4408' b'2848' b'8756' b'2440'
 b'64596' b'160' b'5872' b'67328' b'914476' b'2908' b'2456' b'62996'
 b'264156' b'949352' b'9456' b'12260' b'4692' b'908208' b'2608' b'65932'
 b'30888' b'66476' b'957296' b'57084' b'2144' b'65828' b'4196' b'36488'
 b'89384' b'113192' b'75152' b'7224' b'2348' b'6348' b'79960' b'1232'
 b'4572' b'2520' b'4564' b'2332' b'8104' b'782860' b'6564' b'8444'
 b'83272' b'54524' b'9376' b'999344' b'51372' b'7104' b'1212' b'3144'
 b'3092' b'738512' b'55380' b'611000' b'599536' b'944220' b'57152'
 b'51784' b'2496' b'17452' b'20' b'193816' b'24' b'50876' b'3200' b'22308'
 b'3476' b'7108' b'64088' b'65816' b'911360' b'12556' b'11848' b'3484'
 b'9956' b'55620' b'3744' b'14732' b'14796' b'12176' b'36824' b'5080'
 b'12664' b'78876' b'3488' b'595828' b'9780' b'11944' b'76764' b'584428'
 b'6364' b'68560' b'10428' b'245488' b'6356' b'97080' b'19740' b'7492'
 b'7220' b'60940' b'68512' b'2508' b'51292' b'404832' b'60388' b'5228'
 b'66492' b'191112' b'7632' b'2732' b'908236' b'2568' b'331880' b'67216'
 b'1228' b'7712' b'16800' b'8768' b'3564' b'76200' b'1452' b'68216'
 b'24916' b'1528' b'7508' b'5348' b'7560' b'45528' b'NA' b'34740' b'89688'
 b'44484' b'20808' b'65424' b'957420' b'1184' b'9676' b'70312' b'68572'
 b'84020' b'57496' b'949792' b'4948' b'36388' b'8300' b'75124' b'60444'
 b'5344' b'601112' b'227660' b'99992' b'2256' b'70476' b'2512' b'65836'
 b'6352' b'4700' b'551012' b'36852' b'36504' b'16600' b'9504' b'65096'
 b'120' b'51580' b'44092' b'7668' b'36444' b'32772' b'244148' b'61112'
 b'33412' b'300016' b'48704' b'11924' b'1220' b'24000' b'2516' b'3668'
 b'8216' b'10896' b'52492' b'440168' b'11488' b'785820' b'33044' b'5576'
 b'51716' b'16536' b'18448' b'4524' b'16676' b'64136' b'86924' b'67552'
 b'2148' b'277808' b'205884' b'88716' b'11560' b'65672' b'10036' b'66568'
 b'44480' b'11344' b'92164' b'65148' b'36820' b'908212' b'55064' b'908244'
 b'51484' b'65216' b'32936' b'2488' b'922404' b'3236' b'541232' b'9040'
 b'1740' b'5236' b'10808' b'81512' b'1332' b'3480' b'71080' b'45244'
 b'56804' b'64340' b'8556' b'592792' b'82108' b'12636' b'989708' b'51444'
 b'14524' b'14480' b'577000' b'357996' b'66348' b'60928' b'11768' b'64228'
 b'21676' b'6132' b'5704' b'6212' b'557748' b'50436' b'766024' b'538028'
 b'48412' b'1464' b'3736' b'784484' b'967048' b'36568' b'1240' b'444016'
 b'79408' b'7936' b'912344' b'111260' b'813504' b'122128' b'251808'
 b'247004' b'7884' b'4112' b'36848' b'1328' b'25108' b'8252' b'78308'
 b'96684' b'22848' b'4812' b'41040' b'7984' b'82996' b'87016' b'190232'
 b'92668' b'3344' b'455204' b'8720' b'7616' b'71440' b'12544' b'67704'
 b'71004' b'404856' b'53648' b'816152' b'579468' b'57024' b'61588' b'6156'
 b'2688' b'6548' b'611596' b'110196' b'45572' b'51752' b'179880' b'64096'
 b'93620' b'488608' b'5944' b'10892' b'11732' b'32960' b'3516' b'117412'
 b'5688' b'40456' b'598956' b'11772' b'502228' b'959932' b'54976'
 b'214972' b'5476' b'104968' b'49552' b'405768' b'4104' b'7168' b'501788'
 b'5444' b'113056' b'5388' b'80460' b'214408' b'530380' b'4328' b'43684'
 b'583288' b'175656' b'67244' b'12436' b'1556' b'25784' b'42424' b'48268'
 b'52220' b'7584' b'544116' b'2860' b'12676' b'11044' b'6612' b'14764'
 b'65436' b'82852' b'2776' b'1460' b'4364' b'63380' b'4464' b'76' b'2140'
 b'7876' b'87424' b'65904' b'272088' b'561920' b'15920' b'80780' b'753992'
 b'603544' b'2584' b'11156' b'83900' b'770864' b'76132' b'543076'
 b'379780' b'3096' b'97408' b'51556' b'4248' b'64100' b'34572' b'64636'
 b'70292' b'41516' b'5104' b'80776' b'121356' b'770056' b'3880' b'1272'
 b'538184' b'766544' b'50848' b'3460' b'12656' b'86436' b'54316' b'76252'
 b'200112' b'279408' b'83872' b'2264' b'66532' b'32764' b'36836' b'2152'
 b'24912' b'326180' b'35688' b'2288' b'75928' b'7888' b'74812' b'75256'
 b'45796' b'14560' b'5008' b'957504' b'448748' b'78384' b'2436' b'45364'
 b'56540' b'67688' b'737736' b'36528' b'11468' b'1344' b'54988' b'56'
 b'49452' b'586028' b'76220' b'16696' b'61428' b'2244']
Feature: top_5_90_day_non_fresh_product
Tensor: [b'2192' b'12092' b'1500' b'2572' b'118652' b'1424' b'777928' b'922968'
 b'51580' b'3596' b'54988' b'13860' b'25128' b'736552' b'6664' b'12656'
 b'88' b'1220' b'65336' b'2624' b'62732' b'4408' b'1452' b'949352' b'6364'
 b'85648' b'2872' b'300016' b'66460' b'3600' b'1284' b'2492' b'4192'
 b'1232' b'65428' b'1560' b'541712' b'80460' b'2608' b'99648' b'54980'
 b'64088' b'455204' b'87016' b'66564' b'34580' b'14760' b'5672' b'75124'
 b'12324' b'173052' b'3344' b'1276' b'1356' b'2552' b'16160' b'817352'
 b'113192' b'97792' b'36528' b'4112' b'1352' b'45612' b'5988' b'41864'
 b'73540' b'2144' b'12640' b'51292' b'11220' b'10756' b'17680' b'464592'
 b'9792' b'7152' b'84652' b'21676' b'1228' b'3488' b'56584' b'2352'
 b'2556' b'6348' b'6212' b'2388' b'16524' b'49552' b'19740' b'9416'
 b'51504' b'98044' b'1184' b'12032' b'3200' b'982392' b'2132' b'1472'
 b'2540' b'10104' b'331880' b'6548' b'124696' b'3744' b'6156' b'3828'
 b'1620' b'4284' b'1596' b'450748' b'51304' b'124' b'59868' b'11848'
 b'92232' b'12344' b'65696' b'3120' b'60904' b'598592' b'66348' b'2848'
 b'65096' b'14808' b'12436' b'6448' b'559092' b'10892' b'450624' b'64636'
 b'64952' b'16600' b'56160' b'44796' b'5344' b'108' b'3476' b'1312'
 b'16456' b'2732' b'1368' b'9676' b'5444' b'10296' b'36504' b'293556'
 b'9504' b'8556' b'14628' b'67688' b'10808' b'4656' b'7136' b'5652'
 b'64664' b'10412' b'16272' b'44392' b'5576' b'10036' b'51448' b'7224'
 b'24584' b'78436' b'91936' b'24788' b'9408' b'1324' b'4816' b'4948'
 b'565168' b'4572' b'16236' b'94352' b'12136' b'2508' b'6844' b'169888'
 b'205884' b'41524' b'66376' b'65524' b'51660' b'66760' b'65260' b'186656'
 b'906284' b'538028' b'3144' b'6220' b'3920' b'24' b'12516' b'31112'
 b'16708' b'11444' b'4196' b'41872' b'65420' b'2504' b'31068' b'8216'
 b'12848' b'66320' b'196688' b'61064' b'28' b'964960' b'45440' b'3532'
 b'65444' b'99956' b'5688' b'5704' b'957448' b'375516' b'43976' b'207580'
 b'48408' b'908212' b'3608' b'3124' b'16268' b'45600' b'12176' b'2392'
 b'2568' b'68304' b'84372' b'8384' b'45572' b'15920' b'8500' b'2704'
 b'65436' b'8388' b'10792' b'6032' b'7876' b'NA' b'4520' b'761168'
 b'34748' b'50444' b'81596' b'37576' b'42912' b'10092' b'6568' b'32'
 b'73244' b'51444' b'948284' b'11224' b'4708' b'50708' b'604164' b'66568'
 b'1328' b'11940' b'11656' b'2440' b'28864' b'105716' b'600900' b'9956'
 b'454264' b'7980' b'43196' b'35224' b'76776' b'5184' b'597420' b'54976'
 b'76588' b'944116' b'199800' b'79608' b'22100' b'32936' b'357996'
 b'945672' b'9544' b'3424' b'234900' b'454504' b'1380' b'2412' b'53668'
 b'36312' b'45568' b'1304' b'203404' b'84852' b'3464' b'81016' b'6612'
 b'7108' b'11560' b'2248' b'33108' b'64252' b'20' b'5228' b'603828'
 b'7492' b'74704' b'60444' b'66332' b'2280' b'67644' b'66476' b'809012'
 b'64096' b'42476' b'108940' b'597840' b'2408' b'14560' b'3460' b'2676'
 b'5136' b'1332' b'14500' b'3056' b'65836' b'24940' b'17772' b'989584'
 b'97408' b'78124' b'7880' b'3808' b'16536' b'551012' b'1748' b'300012'
 b'7572' b'908236' b'1572' b'2688' b'174788' b'211980' b'94160' b'65816'
 b'7712' b'3444' b'36568' b'1496' b'16176' b'66088' b'77380' b'11168'
 b'11664' b'89980' b'957296' b'344412' b'48600' b'3880' b'586936' b'57152'
 b'244148' b'24356' b'2180' b'749048' b'54348' b'101384' b'452160'
 b'115332' b'13824' b'10108' b'75584' b'16544' b'5404' b'3060' b'51372'
 b'83048' b'99472' b'96216' b'36848' b'1488' b'9376' b'3384' b'506276'
 b'55620' b'61112' b'908208' b'8768' b'25116' b'4172' b'682952' b'766544'
 b'47852' b'60944' b'49664' b'488608' b'5236' b'51584' b'4328' b'33276'
 b'91720' b'56804' b'71440' b'2348' b'60396' b'7176' b'681956' b'9040'
 b'502584' b'65664' b'169984' b'9768' b'1456' b'989184' b'51752' b'113520'
 b'68276' b'68252' b'36712' b'19172' b'8252' b'14580' b'40360' b'82836'
 b'140256' b'66108' b'682264' b'4564' b'65916' b'12676' b'24916' b'3276'
 b'4380' b'2860' b'11472' b'1248' b'338572' b'36444' b'160' b'592792'
 b'48968' b'40456' b'2208' b'84976' b'1212' b'131140' b'273356' b'6204'
 b'4704' b'48556' b'184192' b'60452' b'55048' b'65812' b'10428' b'582000'
 b'1464' b'9056' b'754876' b'48624' b'7072' b'182520' b'207192' b'744292'
 b'903488' b'82996' b'3284' b'64136' b'66256' b'42444' b'86140' b'452164'
 b'8592' b'14764' b'48264' b'14584' b'6132' b'496468' b'968840' b'231860'
 b'6968' b'84160' b'595828' b'73248' b'9344' b'51484' b'776584' b'5388'
 b'60856' b'44412' b'65496' b'78408' b'113544' b'99880' b'2488' b'499452'
 b'430392' b'51180' b'28660' b'118800' b'5080' b'56592' b'181912' b'168'
 b'218024' b'3700' b'2524' b'3212' b'82364' b'100032' b'12056' b'485780'
 b'94792' b'3736' b'65620' b'48852' b'64100' b'103952' b'4700' b'2140'
 b'724144' b'67976' b'65140' b'14524' b'64824' b'7532' b'404856' b'16652'
 b'82192' b'82248' b'2420' b'24932' b'65932' b'5096' b'20904' b'6392'
 b'1548' b'537168' b'108812' b'17392' b'2776' b'8448' b'24836' b'1256'
 b'966160' b'16696' b'59624' b'16624' b'49764' b'2188' b'5084' b'32800'
 b'16072' b'36488' b'80424' b'3824' b'4524' b'76232' b'544076']
Feature: Total_spend
Tensor: [6.3630461e+04 1.7847666e+04 8.0024941e+03 6.4460698e+03 1.7453709e+04
 4.4308350e+03 8.5073848e+03 5.4749465e+04 6.0934678e+03 2.6506469e+05
 5.5260361e+03 5.0634831e+05 2.9048040e+03 4.8849832e+04 3.9899341e+03
 2.4073496e+04 4.1265925e+05 6.9135029e+03 7.3950122e+03 2.0685727e+04
 1.9158292e+05 9.9065342e+03 6.1226729e+03 4.2850259e+03 1.2993336e+05
 3.5136179e+03 4.1555161e+03 7.0525367e+04 6.2798328e+04 2.1122303e+05
 6.4703608e+03 9.9786416e+03 1.0580913e+05 3.6447086e+04 1.0918341e+04
 4.9065840e+03 1.0415799e+04 2.9817361e+03 3.3996421e+03 1.5835410e+03
 4.4613091e+03 7.0310161e+03 1.1209932e+04 3.9660102e+04 1.5659806e+05
 2.1961225e+04 1.6722324e+04 1.0948554e+04 4.1280122e+03 7.7083921e+03
 4.8530078e+04 8.0993882e+03 3.0368879e+03 4.1956021e+03 1.2900231e+04
 3.1426523e+04 4.8013945e+04 3.8410740e+03 3.4923149e+03 1.0119710e+05
 1.8235871e+04 1.4785452e+04 5.7138301e+03 4.5418408e+03 1.8478260e+03
 1.7515484e+04 2.8042200e+03 5.9766748e+03 2.3800969e+04 4.7289150e+03
 2.8409148e+04 2.1378240e+03 7.3997102e+04 4.9700512e+04 1.4057811e+04
 1.5703983e+04 2.6644409e+03 8.1605342e+03 1.3649616e+04 2.9378654e+04
 2.2111741e+03 1.6654590e+03 2.6117496e+04 2.2319370e+03 4.4717219e+04
 1.3335660e+04 7.2050488e+03 2.1243168e+04 1.6617870e+03 2.4314939e+03
 1.4315310e+03 1.3983948e+04 1.2577806e+04 1.0160154e+04 2.5487371e+03
 7.1774731e+03 1.0491669e+04 1.6287489e+04 1.1454849e+04 1.3574151e+04
 6.9803461e+04 7.7896260e+03 1.7157061e+03 2.2284541e+03 3.2972849e+03
 7.5039945e+04 6.5606401e+03 1.6998120e+03 4.9700249e+03 1.3400452e+05
 5.9882490e+03 1.4794749e+04 3.2037571e+03 2.0560607e+04 8.0513098e+02
 1.1891664e+04 2.3322617e+04 4.0373369e+03 1.6833365e+04 2.5560062e+04
 2.8665271e+03 2.5257023e+04 2.5618860e+03 4.7966221e+03 2.3469867e+04
 3.9382191e+04 2.1625623e+04 5.0223149e+03 6.3071909e+03 1.4730840e+03
 3.9326840e+04 1.1366408e+05 1.7988210e+03 9.6193623e+03 3.7484027e+04
 8.4446553e+03 1.7439436e+04 2.3370229e+04 1.6928234e+04 3.1676373e+04
 3.0247199e+04 4.3958970e+03 1.3936770e+03 2.2222387e+04 3.0671027e+04
 2.9696040e+03 1.2683889e+04 7.5344580e+03 1.2277575e+04 3.2255459e+03
 1.0179900e+03 1.6453395e+04 1.5992181e+04 1.7855244e+04 9.7990830e+03
 5.5740601e+03 1.4874921e+04 1.3768902e+04 1.6253280e+04 1.9738890e+03
 2.3301621e+04 2.3449771e+03 7.9380000e+03 9.9279717e+03 2.5734331e+03
 1.2126756e+05 1.4799780e+03 3.2805630e+03 1.5987492e+04 3.9867930e+03
 1.9269549e+04 2.3541066e+04 2.1637232e+04 2.4963578e+04 8.5394248e+03
 1.9127098e+04 9.6441660e+03 1.2963330e+03 2.7537661e+03 1.7869680e+03
 2.5480629e+04 5.4137070e+03 1.0540107e+04 1.4564160e+03 2.3307346e+04
 1.1812321e+03 6.9923000e+04 9.5675400e+03 2.1890225e+05 1.4745330e+03
 2.7027773e+04 1.0781550e+04 1.9208610e+03 1.7224740e+03 3.6135000e+03
 5.0946238e+04 1.1503134e+04 2.0601324e+04 2.1955320e+03 1.6267140e+04
 5.4060122e+03 3.5473140e+03 2.2800239e+03 2.6021205e+04 2.0494160e+04
 8.9901445e+03 5.3138789e+03 1.2095901e+05 7.6217129e+03 2.7472445e+04
 1.5722208e+04 1.8166859e+04 5.5486260e+03 1.3322045e+05 1.5044670e+03
 2.0736521e+04 6.1443901e+03 2.0135709e+04 1.0527075e+04 3.3466951e+03
 3.0901230e+03 1.5914611e+03 3.1364369e+04 2.1398850e+04 2.0927727e+04
 3.9317246e+04 4.0517801e+04 4.0344148e+04 9.3457354e+03 5.5300322e+03
 1.3312800e+03 1.6288821e+04 1.8186967e+04 1.4124978e+04 1.9823652e+04
 1.4268060e+03 3.4942410e+03 3.4190953e+04 3.2438008e+04 2.3996133e+04
 2.7008101e+03 2.1387959e+03 2.5440930e+03 1.0894950e+03 1.2862764e+04
 4.2295699e+04 1.6813305e+04 1.1815857e+04 1.2211812e+04 5.7083218e+03
 6.4922129e+03 4.4768359e+04 5.2830088e+03 1.7743248e+04 3.6460891e+03
 3.5391150e+03 3.8823301e+03 1.2690783e+04 3.5549109e+04 2.5785404e+04
 1.5673806e+04 2.1799891e+04 2.2000645e+04 1.2210516e+04 1.7239635e+04
 1.8079371e+04 1.2288555e+04 6.9002100e+02 2.0930129e+03 8.5602783e+03
 1.5107508e+04 6.5447965e+04 2.4787710e+03 2.0899980e+03 1.1025179e+03
 8.2720439e+03 4.4599951e+03 2.1554460e+03 4.5672388e+03 3.7963081e+03
 3.8340811e+03 1.1995902e+04 2.2953960e+03 4.7232297e+04 3.3095339e+03
 1.1048517e+04 3.9547351e+03 2.4117930e+03 4.4293742e+04 6.9147469e+04
 1.6935740e+04 2.3458303e+04 1.2322440e+03 2.0087117e+04 5.2606440e+03
 1.5325803e+04 1.8669420e+03 5.3130059e+03 6.4220132e+03 2.5785901e+03
 7.8225210e+03 1.3904595e+04 6.8783398e+02 3.3000300e+03 3.3332310e+03
 4.0760371e+03 3.0056688e+04 2.7268857e+04 4.0367429e+03 2.7417329e+03
 9.5470918e+03 3.3004351e+03 3.5625239e+03 2.8374299e+03 3.5057520e+03
 1.0177929e+04 1.8500635e+04 1.4487300e+03 3.4329600e+03 1.3342518e+04
 2.7136980e+03 4.4535869e+03 1.6344720e+03 3.8091689e+03 4.0800420e+03
 1.0760526e+04 1.3185189e+04 5.6998530e+03 2.2979475e+04 1.9799055e+04
 1.4203530e+03 2.6132581e+03 6.7487310e+03 1.4089068e+04 1.9273950e+03
 1.1536740e+03 1.0479060e+04 7.4049453e+04 1.9926441e+04 8.0525698e+03
 2.8364670e+03 7.3469702e+02 7.6553730e+03 2.2617900e+03 4.4650855e+04
 1.2889008e+04 2.8927800e+03 1.5765210e+03 1.5707907e+04 5.7670469e+03
 5.8961188e+04 1.0849950e+03 2.1077199e+04 8.3107803e+03 1.1358450e+04
 6.6244678e+03 2.7672300e+03 1.3491810e+04 7.8442920e+03 7.9813711e+03
 7.7972671e+03 1.0185327e+04 1.0000152e+04 9.1955156e+03 3.7176389e+03
 1.2437010e+03 1.4885820e+03 4.7274516e+04 1.8914940e+03 3.1994424e+04
 1.3032918e+04 3.5601867e+04 6.5477158e+03 1.4367330e+03 5.0291548e+03
 8.8126924e+03 1.3473216e+04 2.7490410e+03 1.3805551e+03 2.0974994e+04
 2.0205990e+03 8.8212871e+03 5.8471650e+03 1.7150850e+03 1.2267846e+04
 2.2892400e+03 9.1740596e+03 9.6827399e+02 1.4749191e+04 6.6424500e+02
 1.9198494e+04 3.8036195e+04 1.5859800e+03 2.1551399e+03 8.3142266e+03
 1.8012320e+04 2.4913539e+04 2.8046971e+04 4.1707979e+03 1.8374760e+03
 8.8223401e+02 1.4307480e+03 3.4782390e+03 3.1124492e+04 1.1367054e+04
 7.6568940e+03 1.1650905e+04 2.2058010e+03 1.1388150e+04 1.4095350e+03
 3.8484990e+03 2.7018035e+04 8.9519941e+03 6.1488091e+03 6.3395552e+03
 2.4441750e+03 2.6114761e+03 1.0627290e+03 8.4496504e+03 1.7210970e+03
 1.4891688e+04 8.1810718e+03 3.7128781e+04 9.1562852e+03 2.5017930e+03
 2.2382549e+03 4.0922371e+03 1.4157846e+04 1.3602419e+03 1.6727887e+04
 1.3930803e+04 4.0319280e+03 5.6990996e+04 3.2816790e+03 2.3248711e+03
 3.6566785e+04 1.3727430e+03 4.8200220e+03 5.3907300e+03 3.1743359e+03
 8.5340068e+03 4.0669919e+03 1.0171296e+04 6.7312529e+03 1.1475081e+04
 7.9457041e+03 1.6779150e+03 9.2818799e+03 1.3978710e+03 9.1928477e+04
 1.3727340e+04 2.6900640e+03 1.0123884e+04 5.2683208e+03 2.1822930e+04
 1.9892789e+04 2.2559912e+04 1.0062540e+04 3.9573820e+04 8.0108133e+04
 6.3766803e+02 8.5423496e+03 6.9073110e+03 3.8697184e+04 6.8405402e+02
 2.0642697e+04 8.0755539e+04 2.8953793e+04 1.6248357e+04 4.6641152e+03
 2.6585758e+04 8.9499424e+03 1.1655747e+04 2.8129465e+04 1.7048430e+03
 3.0267307e+04 4.1731289e+03 1.9370709e+04 5.2424639e+03 9.6408899e+02
 3.8525581e+03 1.8399951e+04 3.9192749e+03 1.2318571e+03 3.2103369e+04
 2.5864470e+03 2.1794670e+03 1.4180589e+04 1.8565470e+03 1.0943370e+03
 1.7026748e+04 1.1786229e+04 1.2740112e+04 2.9085659e+03 8.6764250e+04
 9.1740508e+03 3.4333020e+03 6.8499180e+04 6.0856831e+03 2.6509861e+03
 9.0038702e+02 8.6999404e+03 5.4486182e+03 1.9715570e+04 2.3016599e+03
 1.1763225e+04 1.8268290e+03 6.1175518e+03 1.4068476e+04 9.8425800e+02
 2.8635012e+04 1.3572054e+04 1.3986027e+04 1.0759707e+04 5.8332241e+03
 1.7768178e+04 1.9501740e+03 1.9851660e+03 7.2273602e+02 4.1108491e+03
 1.2163592e+05 8.1818462e+03 2.8470959e+03 2.6429293e+04 5.2010371e+03
 1.6844580e+03 1.8064457e+04 3.1788540e+03 7.7898508e+04 1.3749831e+04
 8.1744299e+02 2.2321908e+04 1.1569950e+03 1.3033116e+04 3.7556633e+04
 1.0456704e+04 2.0602981e+03 1.6987679e+03 5.7158099e+02 1.7424324e+04
 1.0710000e+04 3.5852490e+03 1.3980690e+03 1.1830320e+03 8.2129590e+03
 1.1704563e+04 2.8341809e+03 1.5680430e+03 1.0477350e+03 1.3290389e+03
 4.3983809e+03 2.6031509e+03 9.2517568e+03 8.0326982e+03 2.2275379e+04
 1.0133370e+03 2.3861431e+03 7.3140571e+03 2.1036889e+04 8.2017178e+03
 7.9247520e+03 1.5720570e+03 1.8526941e+04 1.2207780e+04 1.1066454e+04
 4.5255962e+03 2.2020939e+04 1.1499750e+03 5.7737701e+02 3.7758601e+03
 7.5925620e+03 3.1223537e+04 8.3903223e+03 1.6569540e+03 7.4589302e+03
 1.3873482e+04 2.8453689e+04 4.5752939e+03 2.4961321e+03 8.8400702e+02
 2.7262529e+03 1.0567467e+04 8.4709707e+03 1.4085090e+04 1.0682469e+04
 2.7012348e+04 2.7933760e+04 1.0934523e+04 3.9751021e+03 6.3787051e+03
 1.4683051e+03 1.1756250e+03 9.7632900e+03 5.7246572e+03 1.0141470e+03
 3.5875620e+03 6.3489600e+02 9.3705303e+03 8.2735557e+03 1.1020626e+04
 9.8261553e+03 2.1880566e+04 9.5356797e+03 3.7840680e+04 1.0750590e+03
 1.4838714e+04 5.8719780e+03 2.3659919e+03 1.4252193e+04 1.5931026e+04
 1.8214290e+03 5.1469380e+03 9.9329043e+03 1.4487318e+04 6.6422881e+03
 1.7688662e+04 7.4994658e+03 2.1630779e+03 4.9674238e+03 1.3836870e+04
 4.0290659e+03 2.4665301e+04 3.4809121e+03 7.2074203e+04 1.4767469e+03
 5.8919312e+03 2.7209160e+03 1.4674771e+03 1.9156373e+04 1.2960540e+03
 6.3811348e+03 6.1250581e+03 2.8350604e+04 5.9513491e+03 3.1909320e+04
 1.7042635e+04 1.4978700e+03 3.4237800e+03 9.8669971e+03 4.5715500e+02
 4.1849129e+04 7.8953400e+02 5.3557202e+03 1.6239960e+03 2.7364680e+04
 1.3346784e+04 3.2392080e+03 1.7402273e+04 1.1470293e+04 1.2419082e+04
 1.3559580e+03 1.8111303e+04 5.0786279e+03 1.1353095e+04 2.5572061e+03
 9.9911700e+02 7.9864019e+03 6.1554692e+03 1.2631770e+03 7.1719741e+03
 6.0523199e+02 1.2753423e+04 7.3199429e+03 6.4975500e+02 2.8539027e+04
 1.4032782e+04 2.3418269e+03 5.2116572e+03 5.2908102e+04 8.7907139e+03
 1.5006330e+04 1.0518345e+04 1.0049535e+04 2.2139189e+03 1.3834782e+04
 1.4500755e+04 7.5824639e+03 1.5715980e+03 1.5117876e+04 7.6104360e+03
 4.7776768e+03 1.0369107e+04 8.5090498e+03 7.1018281e+03 1.4376870e+04
 5.4971997e+02 3.9127319e+03 3.5431379e+03 3.0905289e+04 2.8732859e+03
 1.0871595e+04 1.9349370e+03 5.8351230e+03 1.5971940e+03 5.6804580e+03
 1.8003455e+04 3.0913110e+03 1.4354235e+04 5.3502568e+03 1.5234588e+04
 2.2281841e+03 2.1430979e+03 1.0890900e+04 1.2596085e+04 2.7638911e+03
 7.4412002e+03 1.4446620e+03 3.1793553e+04 1.2489327e+04 1.3467195e+04
 2.4062086e+04 2.5323931e+03 9.5085898e+03 7.6746600e+02 1.9352547e+04
 1.6129440e+04 1.2458070e+04 1.1607372e+04 8.5207501e+02 3.1198672e+04
 1.5832531e+03 1.3994181e+04 7.2290610e+03 5.0491709e+03 3.1940289e+04
 5.7108779e+03 4.5688113e+04 2.2196609e+03 7.3796938e+03 1.9919629e+04
 8.8967969e+03 1.8404793e+04 5.2150500e+02 1.6216362e+04 1.7316899e+03
 1.8111689e+04 1.8870975e+04 8.8932598e+03 7.7209111e+03 6.5889422e+04
 1.2393837e+04 3.6274141e+03 3.0771089e+03 4.5262979e+03 1.3061412e+04
 4.7715479e+03 1.1242377e+04 2.2201741e+03 1.0417482e+04 1.3738806e+04
 1.1782305e+04 3.5837129e+04 3.1626721e+03 8.1114028e+03 1.0895445e+04
 2.1441016e+04 1.0462321e+03 7.3851841e+03 5.3036548e+03 1.1984940e+03
 5.5480322e+03 4.2675391e+03 5.0371558e+03 1.0728090e+03 4.6737406e+04
 1.9600316e+04 2.0311434e+04 9.3978900e+02 2.7626805e+04 1.3971150e+03
 6.2990100e+02 2.1517739e+03 1.6855037e+04 3.2178330e+03 4.0012930e+04
 2.3075820e+04 7.3813770e+03 6.3981992e+03 9.2103838e+03 2.8914939e+04
 1.5640291e+03 5.0034512e+03 2.2611060e+03 4.0452949e+04 8.9180820e+03
 7.1424810e+03 6.1789590e+03 2.7846766e+04 7.5700708e+03 1.9832400e+03
 4.1757842e+03 1.6471980e+03 6.8740198e+02 4.2002642e+03 7.9335088e+03
 7.5028950e+03 2.0228266e+04 2.1353401e+03 4.8995459e+03 3.5004780e+03
 1.5580350e+03 7.1652871e+03 1.0692629e+03 1.1958021e+04 1.7308395e+04
 9.8236260e+03 2.7135090e+04 4.0979248e+03 1.6126740e+03 5.3455322e+03
 2.1081438e+04 3.3031746e+04 1.4246550e+04 8.5146594e+04 2.9661299e+03
 1.0687590e+03 2.6223479e+03 1.6763867e+04 1.3446000e+03 1.0795050e+03
 2.0143467e+04 4.6139668e+03 1.6926453e+04 5.9747310e+03 1.4429124e+04
 8.6232422e+03 6.1546547e+04 4.7795308e+03 5.4226982e+03 2.9389319e+03
 1.5881580e+03 4.8300316e+04 4.3887871e+03 8.2188994e+03 6.4676519e+03
 6.2046812e+03 5.9636250e+03 5.2711470e+03 1.3175829e+04 5.9563530e+03
 9.3983936e+03 5.8173032e+03 3.4227262e+04 2.1697290e+03 8.1049500e+02
 1.4942718e+04 1.3107330e+03 8.2610999e+02 7.8549751e+03 3.4241680e+04
 2.0153879e+03 8.8054199e+02 6.5397690e+03 4.8592801e+02 1.2762729e+04
 9.3267266e+03 1.6348347e+04 1.2343329e+04 5.9062861e+03 1.0727955e+04
 1.1396142e+04 1.0006353e+04 3.2971500e+02 1.0778094e+04 4.0826431e+03
 1.9446029e+04 1.9354410e+03 3.2729104e+04 3.5588340e+03 2.4563564e+04
 2.0847061e+03 1.3637034e+04 1.1739042e+04 6.2614711e+04 6.3064980e+03
 5.5869932e+03 7.5142349e+03 1.9318230e+03 5.0558672e+03 1.3602330e+04
 5.2255352e+03 2.6453521e+03 5.4044009e+03 3.2550623e+04 1.0659204e+04
 7.4895300e+02 3.2434741e+03 4.4769512e+03 1.4749695e+04 9.6507898e+02
 3.3928012e+04 2.1107205e+04 1.0950984e+04 1.5468300e+02 5.7525298e+03
 2.9506321e+03 2.5020000e+03 5.7736709e+03 4.0778550e+03 1.6315623e+04
 3.5682749e+03 4.2827041e+03 6.8857202e+02 9.4124883e+03 6.4605962e+03
 7.3093500e+02 1.1755548e+04 2.0572461e+04 2.4360930e+04 7.0939888e+03
 6.9335459e+03 5.2270381e+03 1.4967018e+04 6.2381431e+03 6.9960508e+03
 1.9224360e+03 1.9827540e+03 1.0902240e+04 1.2124341e+04 6.3931050e+03
 6.9288838e+03 7.7309100e+02 2.6992800e+03 1.9304414e+04 4.6471318e+03
 9.4909951e+03 1.2395341e+03 1.1116440e+03 7.2158398e+02 1.6065720e+04
 1.4724360e+03 2.2025339e+03 3.5653148e+04 7.0599512e+03 3.9375000e+02
 1.4223960e+03 3.1674241e+03 7.4845171e+03 8.0970298e+03 7.2121318e+03
 1.2649743e+04 8.7552900e+03 2.0542383e+04 1.3023000e+03 6.7562012e+03
 7.7934601e+02 1.1821050e+03 3.8459367e+04 8.4169346e+03 9.3417930e+03
 1.0707786e+04 6.7090771e+03 7.5013202e+02 1.7379855e+04 9.0958502e+02
 2.0786760e+03 2.1323069e+03 1.1745990e+03 5.7529797e+02 1.1286495e+04
 1.5032700e+03 1.2886794e+04 1.1760210e+03 5.4972720e+03 5.5527301e+02
 1.3597605e+04 3.2956379e+03 8.7885723e+03 1.9974547e+04 1.1402100e+04
 1.7538184e+04 1.4122755e+04 1.0198143e+04 2.6871030e+03 2.6461621e+03
 6.1675649e+03 2.3935420e+04 8.8631367e+03 3.3026760e+03 4.4207999e+02
 1.2820590e+03 1.1647188e+04 5.9496118e+03 1.6075314e+04 6.3158102e+04
 5.7333418e+03 6.4805581e+03 1.3476249e+04 1.3629871e+03 1.1532519e+04
 1.3631697e+04 9.5064658e+03 2.9976841e+03 5.1036211e+03 5.9934601e+02
 7.2222842e+03 4.9901938e+03 2.9435491e+03 1.0286100e+04]
Feature: Total_trx
Tensor: [660. 572. 571. 568. 554. 523. 516. 498. 479. 459. 456. 426. 424. 416.
 408. 404. 401. 399. 397. 394. 389. 372. 364. 355. 354. 347. 343. 338.
 334. 326. 321. 319. 317. 315. 313. 312. 304. 301. 298. 295. 291. 290.
 288. 287. 286. 284. 280. 277. 276. 275. 273. 268. 267. 262. 260. 259.
 258. 255. 254. 252. 251. 249. 248. 245. 244. 243. 242. 241. 239. 238.
 237. 235. 233. 232. 229. 228. 225. 224. 223. 222. 221. 220. 219. 218.
 217. 216. 215. 214. 213. 211. 210. 209. 207. 206. 205. 203. 202. 201.
 200. 199. 198. 197. 194. 193. 192. 191. 189. 188. 187. 186. 185. 184.
 183. 182. 181. 180. 179. 178. 177. 176. 173. 172. 171. 170. 169. 168.
 167. 166. 165. 164. 163. 162. 161. 160. 159. 158. 157. 156. 155. 154.
 153. 152. 151. 150. 149. 148. 147. 146. 145. 144. 143. 142. 141. 140.
 139. 138. 137. 136. 135. 134. 133. 132. 131. 130. 129. 128. 127. 126.
 125. 124. 123. 122. 121. 120. 119. 118. 117. 116. 115. 114. 113. 112.
 111. 110. 109. 108. 107. 106. 105. 104. 103. 102. 101. 100.  99.  98.
  97.  96.  95.  94.  93.  92.  91.  90.  89.  88.  87.  86.  85.  84.
  83.  82.  81.  80.  79.  78.  77.  76.  75.]
Feature: Total_item
Tensor: [3381. 1880.  969.  889. 2372.  772. 1207. 1875.  993. 1438.  691. 1328.
 1206. 2521.  575. 1520. 6237.  561.  964. 1603. 3256.  869.  628. 1165.
 4118.  801.  660. 2023. 1869.  890.  625.  970.  937. 1787. 1048.  770.
  481.  428.  768.  472.  719. 1445. 4145. 4059.  965.  920.  900.  534.
 2263.  739.  589.  478.  800. 1684. 2357.  484. 1469. 1958. 2194.  644.
  767.  535.  435. 1144.  645.  581.  885.  646. 1382. 1212. 2026. 1478.
 1300.  454.  837. 1377. 1374.  636.  505.  968.  370. 2129. 1226.  871.
 1013.  677.  391.  325.  672.  888.  736.  670. 1129. 1474. 1210. 1161.
 2436.  577.  464.  418.  296. 1133.  726.  400.  794.  619.  887.  680.
  515.  287.  688. 1864.  398. 1211.  854.  389. 1337.  394.  913. 1459.
 1702. 1448.  423.  393. 1301. 3271.  384.  488. 1171.  567.  962. 1086.
  910. 1293. 1921.  437.  366. 1118. 1227.  572.  533.  632.  608.  491.
  251.  754. 1115.  986.  676.  724. 1295. 1014.  675.  412. 1036.  386.
  743.  576. 3939.  429.  522. 1660. 1565.  981. 1512.  734.  985.  549.
  314.  495.  420. 1532.  379.  893.  338. 1015.  301. 2869.  651. 1616.
 1195.  274.  365.  350.  823.  580. 1176.  511.  821.  527.  415.  413.
  822. 1317.  732.  585.  874.  661.  878.  387.  816.  297. 1529.  458.
 1192. 1471.  381.  348. 1619. 1163. 1611.  583. 1463. 1666.  952.  385.
  356. 1231. 1649.  461. 1066.  538. 2852. 1077. 1535.  291.  207.  547.
 1553.  796.  777.  835.  306.  310.  352.  448.  532.  759.  403.  344.
  703. 2050. 1172.  329. 1297. 2337.  933. 1274.  915.  183.  337.  654.
 1434.  307.  209.  267.  545.  480.  311.  354.  596.  468. 1157.  558.
  493. 2113. 1050.  498. 1028.  217. 1053.  313. 1012.  193.  245. 1400.
  233.  216.  390.  210. 1353. 1997.  304.  388.  652.  326.  617.  276.
  662.  975.  327.  826.  238.  320. 1201.  811.  280. 1146. 1189.  212.
  512.  786.  184. 1061.  998.  524.  303.  191.  258. 1723.  643.  248.
  187.  525. 1439.  224.  839.  709. 1101.  286.  611.  502.  185.  664.
  396.  462.  336.  790.  180.  789.  784.  275.  263.  921.  761.  926.
  242.  474.  566.  696.  288.  203.  824.  299.  733. 1296.  243.  255.
  932. 1398. 1017.  542.  341.  240.  223.  157.  529.  667.  704.  776.
  261.  649.  699.  457.  346.  232.  204.  663.  514.  820.  792.  257.
  312.  673.  298. 1137.  550. 1235.  471.  427.  689.  324.  383.  614.
  285.  206.  769.  504.  674.  506.  188.  987.  368. 1515. 1175.  902.
 1143.  208.  283. 1786. 1004. 1659.  977.  697.  422.  752. 1002. 1220.
  317.  978.  439.  200.  250.  397.  202. 1246.  360.  723.  160.  687.
  382.  633.  262.  612.  465.  222.  657. 1126.  246.  281.  169.  706.
  765. 1179.  641.  563.  220.  164.  345. 1949.  631. 1566.  603.  241.
 1470.  742.  168.  574.  227.  861.  523.  154. 1040.  361.  309.  152.
  330.  319.  229.  530.  573.  679.  247.  499.  943.  896.  355.  606.
  374. 1316.  225.  155.  268.  997.  271.  186.  289.  541. 1001.  903.
 1039.  833.  278.  256.  115.  239.  470.  178.  117.  459.  803.  698.
 1202. 1102.  162.  980.  433.  357. 1229.  335.  648.  879.  449.  996.
  235.  249.  731.  228. 1668.  165. 1365.  147.  333.  166. 1441.  489.
  901.  618.  745.  293.  182.  475.  219.  294.  124.  582.  593.  148.
 1815. 1062.  367.  856.  376.  705.  340.  305.  895.  146.  211.  339.
  961.  946.  264.  145. 1032.  778.  815.  774.  153. 1186.  989.  455.
  483.  509. 1396.  358.  137.  215.  510. 1867. 1214.  194.  466.  409.
  445.  813. 1437.  231.  161.  362.  451.  218.  501. 1443.  277.  172.
  979.  728.  432.  519.  269. 1204.  668. 1109.  176.  199.  322.  702.
  830.  252.  621.  205. 1432.  831.  834.  375.  159. 1303.  773.  144.
 1621.  300.  988.  876. 1279.  482.  414.  197.  170.  369.  452.  290.
 1242.  171.  174.  995.  112.  517. 1221.  421.  782. 1150.  843.  460.
  624.  497.  479. 1131. 1335.  410.  328.  221.  456. 1181.  949. 1268.
   84.  343.  477.  444.  121.  840.  129.  332.  791.  436.  132.  167.
  441. 1197.  318.  425.  103.  347.   99.  130. 2231.  177.  111.  513.
  690.  142.  588.  715.  579.  123.  122.  805.  113.  151.  295.  116.
  555.  244.  377.  559.  620.  363.  364.  653.]
Feature: Total_unique_items
Tensor: [ 687.  323.  218.  166.  644.  227.  508.  373.  172.  818.  182.  776.
  163.  252.  138.  355.  840.  207.  176.  402.  810.  161.  224.  367.
  551.  204.  319.  381.  420.  585.  148.  372.  279.  421.  275.  294.
  206.  118.  191.  112.  277.  304.  414.  537.  622.  347.  336.  193.
  186.  461.  195.  179.  208.  267.  519.  451.  120.  246.  540.  478.
  316.  192.   70.  500.  165.  175.  296.  216.  525.  117.  566.  484.
  506.  299.  350.  428.  343.   76.  701.  358.  412.  162.  145.   77.
  190.  245.  139.  147.  146.  426.  693.  234.  328.  606.  144.   88.
  397.  417.   94.   78.  401.  311.  203.  150.  433.   53.  352.  563.
  496.  390.  121.  364.  860.  342.  128.  362. 1023.   93.  220.  610.
  313.  383.  379.  408.  721.  173.   68.  423.  511.  196.  302.  243.
  254.  300.  436.  283.  580.  415.   86.  305.  233.  238.  122.  998.
  141.  125.  526.  564.  425.  431.  331.  132.  601.  387.  135.  466.
  136.  649.  291.  635.  156.  384.  137.  124.  293.  171.  483.  134.
  276.  340.  169.  232.  326.  345.  266.  363.  178.  376.   57.  579.
  403.  151.  608.   90.  140.  627.  554.  237.  734.  361.  507.  757.
  108.   91.  873.  354.  595.  157.   55.  258.  573.  223.  255.  185.
  142.  230.  183.   80.  399.  546.  771.  389.  527.  468.  231.  272.
  509.   72.  101.  143.  214.  215.  129.  458.  646.  187.  280.  398.
   73.  536.  159.  439.  181.   95.  149.  329.  104.  490.  131.  152.
  382.  177.  386.   89.   60.  346.   49.   61.  394.  493.  155.  103.
  679.  239.   87.  242.  502.   75.  380.  317.  325.  205.  263.  244.
  282.  339.  180.   67.  213.  259.  188.  174.  241.  113.  116.  249.
  260.  515.   46.  123.  473.  393.  119.  133.   98.   84.   39.  256.
  341.  322.  335.  160.  153.  114.  269.  111.  310.  450.  210.  109.
  235.  290.   96.  392.  168.  236.  226.  219.  495.  158.  324.  378.
  285.   79.  248.  593.   85.  630.  274.  308.  407.  440.  154.  334.
   97.  598.  229.   42.  321.  303.  271.  247.   63.  200.  567.  501.
  437.  253.  438.  422.  314.  883.  514.  265.   81.  388.  198.   50.
  643.   74.  281.  457.   99.   66.   16.  197.   54.  353.  225.  395.
   17.  199.   32.  301.  513.  418.  444.  307.  662.  452.  424.  170.
  529.  106.   59.  617.  429.  574.  333.   92.  105.   47.   35.   64.
  672.  467.  222.   33.  130.  287.   58.  228.   31.  273.   65.  453.
  479.  441.  427.  202.  465.   36.  209.  456.  743.   83.  535.  520.
   40.  360.  126.  351.  619.  375.  261.  107.  270.  521.  348.  406.
  447.  652.  250.  560.  356.  708.   24.  289.  833.  315.   25.  201.
  682.  240.  184.   82.   41.  518.   44.  221.  257.   38.  212.  102.
  725.  298.  368.   37.   51.  531.  416.  309.   19.]
Feature: Total_unique_subclasses
Tensor: [236. 116. 101.  78. 200. 198. 139.  90. 240. 256.  84. 130. 155. 249.
 111.  85. 187. 274.  83.  97. 142. 219. 148. 160. 161. 210.  66. 166.
 182. 109. 133. 123.  62.  57. 132. 117. 201. 213. 156. 168. 141.  88.
  75. 181.  93.  77.  99. 134. 207. 192.  76.  98. 211. 177. 143.  95.
  33. 197. 122. 110. 216.  53. 194. 174. 176. 103. 175.  67. 171.  32.
 221. 164.  68.  51.  74. 217.  69. 151. 220. 128.  70.  82.  39. 169.
  42.  36. 159. 135. 102. 183.  34. 157. 184. 172.  60. 290.  92.  64.
  45. 296.  49. 237.  50. 170. 235.  96. 195.  30. 215. 153.  58. 154.
  81. 113.  59. 289.  63. 158. 165. 185. 149.  72.  40.  61. 189. 228.
 144. 108.  86.  87. 137. 191. 150.  89. 119. 145. 131. 138. 146.  80.
 208.  48.  27.  73. 152. 223. 136. 243. 255. 120.  56.  79.  38. 212.
 105.  94. 230. 127.  35. 125.  37.  47. 115.  71. 251. 167. 199.  41.
 186.  65. 129. 121.  28. 241.  52. 106. 104. 100.  43.  44. 126. 233.
  23.  55.  15. 162. 118. 193. 218.  54.  24.  26. 206. 178. 276. 231.
 190. 163. 112.  31.  12. 173.   9.  91. 188. 140. 196.  29. 114.  13.
  14. 205. 107. 180. 179.  17. 281. 202.  19. 124.  46. 224. 203.  11.
 284.  16. 238.  25. 226. 209.  22.]
Feature: Total_unique_subdepartments
Tensor: [68. 42. 41. 34. 66. 55. 69. 48. 43. 84. 33. 36. 56. 39. 60. 75. 47. 77.
 38. 40. 54. 74. 44. 50. 62. 70. 30. 63. 51. 61. 53. 35. 24. 49. 67. 71.
 52. 58. 45. 19. 59. 46. 31. 57. 65. 17. 26. 29. 21. 22. 28. 20. 27. 64.
 85. 92. 76. 79. 32. 37. 13. 16. 25. 18. 81. 23. 72. 10.  9. 11. 14. 15.
 78.  7. 73.  6. 87.  5.  8.]
Feature: Min_spend
Tensor: [0.    0.54  0.36  0.054 0.189 0.414 0.351 0.45  0.117 0.558 0.288 0.846
 0.162 0.495 0.09  0.855 0.027 1.035 0.468 0.405 0.675 0.531 0.756 0.9
 0.27  0.18  0.009 0.423 0.342 0.144 0.126 0.315 0.252 0.081 0.306 0.918
 0.207 0.828 0.738 0.225 0.477 0.261 0.792 0.099 0.279 1.044 0.693 0.432
 0.72  0.513 0.072 0.369 0.216 1.026 1.755 1.35  0.396 0.378 0.036 0.171
 0.153 0.333 0.873 0.612 0.594 1.116 0.639 1.107 0.666 0.711 0.486 0.585
 1.575 0.81  1.125 0.504 0.657 1.8   0.324 0.621 0.063 1.089 0.927 1.305
 0.603 0.981 0.576 0.882 0.441 2.34  0.999 0.801]
Feature: Max_spend
Tensor: [1.6155000e+03 8.0352002e+02 2.7288000e+02 9.8550003e+01 3.4425000e+02
 1.0350000e+02 1.0800000e+03 5.7109497e+02 4.4910001e+02 1.7887500e+04
 1.9800000e+02 5.2125121e+04 6.2955002e+01 5.8158002e+02 4.0410001e+02
 9.6408002e+02 8.3531250e+03 5.0139001e+02 2.2302000e+02 4.3739999e+02
 9.0000000e+03 1.2780000e+03 2.2387500e+02 5.1066002e+01 1.3795200e+03
 3.5910001e+02 2.5848001e+02 2.3850000e+03 6.9254999e+02 2.1357945e+04
 1.0120950e+03 1.6159500e+02 8.8695000e+03 2.4259500e+02 1.9542599e+02
 1.4039999e+02 4.9950000e+02 6.1200000e+02 7.3980003e+01 1.2600000e+02
 4.1849998e+01 1.9782001e+02 2.6639999e+02 5.3208002e+02 8.1000000e+02
 7.4358002e+02 4.7137500e+02 2.8309500e+02 1.8000000e+02 1.2456000e+03
 1.1599200e+03 8.4941998e+02 1.1862000e+02 1.3139999e+02 3.2359500e+02
 5.1637500e+02 4.8438000e+02 4.0320001e+02 7.1639999e+01 2.9743201e+03
 4.3560001e+02 8.4375000e+02 7.9019997e+01 1.5349500e+02 1.6200000e+02
 1.4539500e+02 8.0459999e+01 2.7539999e+02 1.1647800e+03 1.0746000e+02
 1.2643199e+03 3.3750000e+02 1.4382000e+04 7.7422498e+02 2.4989400e+02
 3.3782401e+02 1.7010001e+02 1.9057500e+02 1.4543550e+03 4.0230000e+01
 9.7465503e+02 4.8195000e+01 5.9453998e+02 1.2406500e+02 2.0466000e+02
 3.8717999e+02 5.0355000e+01 2.4637500e+02 3.0555000e+01 4.3875000e+02
 1.7550000e+02 1.0804500e+03 4.5855000e+01 1.3315500e+02 1.4328000e+02
 5.6996997e+02 3.6382501e+02 1.3567500e+02 1.8855000e+03 1.2960000e+03
 1.2420000e+02 2.1582001e+02 8.7750000e+02 7.2900000e+03 2.7945001e+02
 4.4099998e+01 1.5750000e+02 3.9409738e+04 1.1745000e+02 4.2637500e+02
 6.0750000e+01 2.0700001e+01 1.1844000e+03 4.1220001e+02 3.5639999e+02
 3.6097198e+02 8.9887500e+02 5.1678003e+02 8.0550000e+02 7.1820000e+01
 1.9845000e+02 5.9400000e+02 2.0691001e+03 5.3887500e+02 8.3834999e+01
 1.4073750e+03 6.5245502e+02 5.0220001e+01 5.4000000e+02 7.1550000e+02
 5.2699500e+02 5.2209003e+02 5.4647998e+02 8.0482501e+02 6.4638000e+02
 5.0328000e+02 1.4175000e+02 6.0255001e+01 8.9775000e+02 9.4770001e+02
 5.3909998e+02 1.7514900e+02 2.2860001e+02 1.2240000e+03 1.4382001e+02
 1.3729500e+02 5.6879999e+02 3.0167999e+02 1.2600000e+03 1.0422000e+02
 4.0932001e+02 1.1323800e+03 1.1137500e+03 8.9099998e+01 4.0500000e+02
 8.5680000e+01 3.8815201e+02 3.1387500e+02 1.0113750e+03 4.4955002e+01
 8.2620003e+01 4.6979999e+02 6.2577000e+01 1.0395000e+02 1.9278000e+02
 7.9128003e+02 1.3950000e+02 1.4619600e+03 6.2099998e+01 5.0714999e+02
 6.2550000e+02 1.7262000e+02 5.3099998e+01 1.2895200e+03 8.0099998e+01
 3.8664001e+02 3.7440000e+03 1.3410001e+02 8.9550000e+02 2.0862000e+02
 8.0595001e+01 7.2900002e+01 1.8900000e+02 2.5020000e+03 5.8320001e+02
 1.9953000e+02 9.6794998e+01 1.7280000e+02 2.1222000e+02 6.4440002e+01
 5.8500000e+02 3.0510001e+02 2.4120000e+02 5.0220000e+03 2.9160001e+02
 5.7312000e+02 9.8550000e+02 5.3550000e+02 3.1607999e+02 6.3072000e+04
 5.3306999e+01 1.5462000e+02 4.4887500e+02 3.7439999e+02 6.9750000e+01
 3.9738599e+02 2.6239499e+02 4.4437500e+02 2.5272000e+03 1.2939750e+03
 5.1479999e+02 3.8137500e+02 2.4839999e+02 2.1937500e+02 4.8289499e+02
 4.6619999e+01 3.6000000e+02 7.5537000e+02 7.1279999e+02 1.7982001e+02
 1.2608100e+02 1.0678500e+02 1.8792000e+03 3.9375000e+02 3.2238000e+02
 9.5400002e+01 6.3102600e+02 7.8637500e+02 4.1356802e+03 2.4408000e+02
 7.9199997e+01 1.0425601e+03 2.8728000e+02 1.4191200e+03 6.8832001e+02
 6.7189502e+02 4.1895001e+02 1.8180000e+02 6.7500000e+01 1.5767999e+02
 2.4559199e+03 9.0000000e+01 1.6767000e+02 1.1520000e+02 1.9439999e+02
 1.0980000e+02 5.8409998e+02 1.1250000e+02 5.3207098e+02 1.2637800e+02
 6.8620502e+02 5.2650000e+02 1.4580000e+02 2.0286000e+03 8.3654999e+02
 2.0088000e+02 2.0700000e+02 4.5000000e+01 1.6119000e+02 1.5525000e+02
 2.6865000e+01 8.0959497e+02 8.2312201e+02 3.0642300e+02 7.9379999e+02
 4.8555000e+01 2.2950000e+02 8.4599998e+01 1.2109500e+02 7.4749500e+02
 2.2320000e+02 2.3652000e+02 2.4300000e+02 5.6137500e+02 1.2942000e+02
 7.0199997e+01 1.7739000e+02 4.0387500e+02 6.5609998e+02 2.4282001e+02
 2.8656000e+02 2.8979999e+02 1.0800000e+02 5.5755001e+01 1.7779500e+02
 2.2843799e+03 1.8589500e+02 6.0750000e+02 2.4299999e+01 2.6910001e+02
 3.3048001e+02 4.6800000e+02 7.3125000e+01 1.1627550e+03 2.5069501e+02
 1.5112800e+03 3.1679999e+02 2.6729999e+02 4.1625000e+02 2.5920001e+02
 9.3109497e+02 2.8090799e+02 1.6969501e+02 3.0375000e+03 8.7840002e+02
 4.3312500e+02 4.0455002e+01 2.2500000e+03 1.6758000e+03 2.1872701e+02
 2.8800000e+02 2.6945999e+02 2.4750000e+02 1.0303199e+03 1.7910001e+02
 2.2639500e+02 3.2039999e+02 5.4450001e+01 5.6088000e+02 3.0420001e+02
 2.8023300e+02 4.3020000e+01 2.0079900e+02 1.2672000e+03 9.3150002e+01
 4.3699500e+02 1.0999800e+03 4.2020099e+02 4.4928001e+01 1.1610000e+02
 2.2517999e+02 7.0559998e+02 3.0600000e+02 1.5890401e+02 4.2750000e+02
 4.8599998e+01 7.0875000e+01 1.8123750e+03 8.9447400e+02 2.5560001e+02
 6.4800003e+01 1.3122000e+03 1.5616801e+03 2.9564999e+02 3.8610001e+02
 3.6409500e+02 3.4020000e+01 1.2157200e+02 1.5863400e+03 6.0750000e+03
 6.1154999e+01 1.8810001e+02 1.4377499e+02 4.2839999e+02 4.9679999e+02
 5.6700000e+02 2.3895000e+02 3.7260001e+02 9.7199997e+01 2.6550000e+02
 1.2888000e+02 2.1217949e+03 2.7000000e+02 2.1771001e+02 2.7013501e+02
 1.4947200e+03 9.6479999e+02 4.9455002e+01 1.5565500e+02 5.1557397e+02
 1.9800000e+03 1.3090050e+03 1.2458250e+03 1.3972501e+02 3.0942001e+02
 1.1925000e+02 4.9500000e+02 1.2919501e+02 1.0915200e+03 1.8333900e+02
 1.0710000e+02 6.1559998e+02 3.2400000e+02 8.2800003e+01 6.1020000e+01
 1.6098750e+03 7.9200000e+02 5.8174199e+03 9.4454999e+02 9.8099998e+01
 3.6720001e+02 2.3400000e+01 2.6365500e+02 1.3387500e+02 4.4550000e+02
 5.6870998e+01 6.8040002e+02 1.8603000e+02 1.6214400e+02 2.5757999e+02
 9.4500000e+01 1.8225000e+01 9.6300003e+01 1.9381949e+03 3.8475000e+02
 2.9929501e+02 2.8439999e+02 5.3955002e+01 1.0449000e+03 1.7955000e+03
 5.7599998e+01 5.1785999e+02 4.4549999e+01 1.0348200e+02 2.8782001e+02
 4.9387500e+02 9.9000000e+01 1.0489500e+02 5.9355000e+01 1.0620000e+02
 1.0260000e+02 1.6645500e+02 9.6840002e+02 2.7939600e+03 4.2984000e+02
 3.0739499e+02 6.1875000e+01 1.5031799e+02 1.8539999e+02 9.3712500e+02
 6.4620003e+01 2.9520001e+02 8.6220001e+01 1.9380600e+02 3.3210001e+02
 5.2531201e+02 1.9399500e+02 6.4728003e+02 3.5820001e+02 2.4752699e+02
 9.1540802e+02 8.0055000e+01 1.5795000e+02 5.6609998e+02 6.4754997e+01
 1.1448000e+02 2.6463599e+02 8.7317999e+02 5.9534998e+02 1.2034080e+03
 2.5182001e+02 1.4364000e+02 6.4476001e+02 5.0062500e+02 2.8125000e+02
 6.2072998e+02 1.6182001e+02 1.5300000e+03 2.0700000e+03 1.8420300e+02
 2.1923100e+02 2.2500000e+02 3.1526550e+03 3.0916800e+02 1.3364999e+02
 3.9419998e+01 1.1502000e+02 1.1655000e+03 1.1142000e+02 9.9764999e+01
 4.3375500e+02 2.3750999e+02 1.8630000e+02 6.2887500e+02 8.6372998e+02
 4.4872198e+02 2.0610001e+02 2.9119501e+02 1.0764000e+03 6.8220001e+01
 4.6575001e+01 2.2503600e+02 8.8110001e+01 6.6240002e+02 2.4555600e+02
 3.1995001e+01 2.2967999e+02 3.1680000e+03 5.2541998e+02 4.5562500e+02
 6.7878003e+02 9.8177399e+02 3.5478000e+02 2.8350000e+02 1.0148400e+02
 1.5822000e+02 2.2890601e+02 2.1600000e+01 3.8250000e+02 2.9610001e+02
 9.2018701e+02 9.3123001e+01 4.5792001e+02 5.2154999e+01 3.2673599e+02
 2.4417000e+02 1.6902000e+02 3.3906601e+02 2.3382001e+02 4.0297501e+02
 3.4335901e+02 3.7754999e+02 8.3699997e+01 1.9125000e+02 7.4330103e+02
 2.1829500e+02 2.0655000e+03 1.6560001e+02 3.0209399e+02 2.4255000e+02
 3.3992999e+02 2.1019501e+02 5.4000000e+01 7.8042603e+02 7.2900000e+02
 1.8604800e+02 1.6380000e+02 1.5860160e+03 4.1282999e+02 1.8459000e+03
 8.2521004e+01 2.3310001e+02 4.5198001e+02 7.9468201e+02 9.1871997e+02
 6.3288000e+02 2.1528000e+02 3.2140801e+03 3.8029501e+02 1.2582000e+02
 1.5120000e+02 2.9691000e+02 3.8025000e+02 2.0209500e+02 5.0400000e+02
 2.2173750e+03 1.4400000e+02 3.3300000e+02 2.9565001e+01 4.2120001e+02
 4.2525002e+01 2.1328200e+02 1.6119000e+03 8.3700000e+02 1.4256000e+03
 9.3419998e+01 3.0923999e+02 7.6500000e+01 4.9045499e+02 3.2121899e+02
 5.1889951e+03 1.4086440e+03 5.6250000e+02 1.8144000e+03 6.8850000e+02
 1.0942200e+02 2.6622000e+02 5.2200001e+01 2.4480000e+02 6.9300003e+01
 1.7212500e+02 4.3064999e+01 8.6112000e+02 2.0655000e+02 1.0062000e+02
 8.1675003e+01 2.6262000e+02 8.6400002e+01 9.0666000e+01 1.9755000e+03
 3.5820000e+01 6.4817549e+03 5.1750000e+01 2.6279999e+02 1.4310001e+02
 7.1909998e+02 1.7820000e+02 2.1239999e+02 2.5891201e+03 3.7125000e+02
 2.0137500e+02 1.0935000e+02 3.1310549e+03 2.0520000e+02 8.9955002e+01
 1.9062000e+02 5.0625000e+01 5.8455002e+01 1.3219200e+03 2.2752000e+02
 2.1465000e+01 3.3462000e+02 2.3713200e+02 1.5852600e+02 1.7369550e+03
 7.9825500e+02 3.4542001e+02 7.7597998e+02 1.4760001e+02 1.0782000e+02
 3.3839999e+02 4.5319501e+02 1.9764000e+03 2.2011301e+02 1.3968000e+03
 7.8847198e+02 2.3625000e+02 1.3490100e+02 8.9582397e+02 5.9400002e+01
 2.8079999e+02 3.2670001e+02 2.8799999e+01 7.2827998e+03 4.8559500e+02
 1.5265800e+02 7.0200000e+00 8.9909998e+02 7.8300003e+01 8.8695000e+01
 1.0897200e+02 2.3355000e+01 1.3671000e+03 3.2541299e+02 1.6402499e+02
 5.0220001e+02 3.1410001e+02 4.1022000e+02 1.5115500e+02 2.0025000e+02
 9.4724998e+01 1.0125000e+02 1.0687500e+03 4.2300000e+02 1.2220200e+02
 1.6200001e+01 1.2150000e+02 1.0080000e+02 2.8998001e+02 5.1767999e+02
 3.0083401e+02 3.4560001e+02 1.7100000e+01 8.2620001e+02 2.6689499e+02
 1.9314900e+02 5.4917999e+02 7.5419998e+01 1.4022000e+02 2.5650000e+01
 1.9422000e+02 6.2283600e+02 2.0286000e+02 2.7360001e+02 1.0617750e+03
 5.0179501e+02 2.2885201e+02 1.0324800e+02 7.1887500e+02 1.8225000e+02
 1.5795000e+01 2.7807300e+02 8.1000000e+01 3.8655000e+03 1.1313000e+02
 1.5255000e+03 1.0368000e+03 3.9239999e+02 8.6564697e+02 3.2220001e+01
 1.3770000e+02]
Feature: days_since_last_purchase
Tensor: [  0.   2.   1.  32.  37.  82.  36.   4.  12.  40.   3.   9.   5.   8.
  34.  16.  51.  43.  20.  13.  26.  45.  21.  35.  17.  22.  15.  42.
  46.  30.   6.   7.  59.  41.  69.  44.  57.  28. 134.  10.  39.  38.
  95.  98.  88.  23.  11.  58.  25.  66. 163.  90.  54.  14.  19.  24.
  52.  50.  72.  62.  33.  64. 140.  49. 130.  76.  48.  89.  31. 170.
  93. 139.  56.  67.]
Feature: days_since_first_purchase
Tensor: [241. 240. 239. 235. 229. 236. 178. 234. 223. 231. 226. 208. 232. 228.
 237. 214. 157. 222. 194. 238. 166. 188. 230. 233. 193. 177. 221. 148.
 164. 215. 185. 219. 200.  70.  77. 147. 218. 174. 220. 227. 199. 196.
 213. 224. 173. 225. 169. 211. 126.  85. 195. 170. 165. 206. 205. 163.
 192. 144. 113. 149. 139.  55. 210. 159. 132. 204. 136. 175. 191. 197.
 201. 189. 158. 168. 212. 127. 125. 146.  80.]
Feature: spend_per_trx
Tensor: [  96.40979     31.202213    14.014875    11.348715    31.50489
    8.47196     16.48718    109.93869     12.721228   577.483
   12.039294  1110.413        6.3701844  114.67097      9.410222
   57.868984  1011.41974     17.11263     18.304485    51.58535
  480.15768     24.953485    15.53978     11.015491   349.28323
    9.652797    11.705679   199.2242     177.39641    608.7119
   18.864027    29.09225    313.04477    109.12301     33.491844
   15.285309    32.65141      9.347135    10.724422     5.0271144
   14.162886    22.320686    35.81448    127.115715   515.1252
   72.96088     56.11518     37.113743    13.993261    26.489319
  167.3451      28.122875    10.581491    14.618822    45.1057
  110.65678    171.47838     13.8666935   12.653316   367.98944
   66.798065    55.169598    21.400112    17.335272     7.1070232
   67.36725     10.827105    23.075966    92.251816    18.329128
  111.408424     8.383623   291.32718    195.67131     55.34571
   62.317394    10.573178    32.51209     54.817734   118.46232
    8.916024     6.7155604  105.312485     9.109947   182.51927
   54.654343    29.650408    87.781685     6.895382    10.173615
    5.9896693   58.756084    52.847923    42.869846    10.754165
   30.542439    45.02862     69.90339     49.16244     58.50927
  304.8186      34.165028     7.5250263    9.90424     14.720022
  334.99976     29.41991      7.622475    22.287107   603.62396
   27.09615     67.248856    14.562531    93.457306     3.6763973
   54.548916   106.98449     18.60524     77.57311    117.78831
   13.209802   116.391815    11.860583    22.206583   109.16217
  183.17299    101.05431     23.468761    29.472855     6.9158874
  184.63306    538.6923       8.525218    45.589394   178.49538
   40.40505     83.442276   112.89965     81.778915   153.7688
  146.83107     21.339306     6.7984242  108.401886   149.61478
   14.485873    61.87263     37.115555    60.480663    15.889389
    5.0395546   81.45245     79.16921     88.83206     48.751656
   27.8703      74.3746      69.19046     82.08727      9.969136
  117.68495     11.843318    40.090908    50.395798    13.265119
  625.0906       7.6287527   16.997736    83.26819     20.764547
  100.362236   123.251656   114.48271    132.78499     45.665375
  102.28394     51.850353     6.9695325   14.805194     9.6592865
  137.73312     29.422321    57.28319      7.9585576  127.36254
    6.4548197  384.1923      52.859337  1216.1237       8.19185
  150.99315     60.232124    10.731067     9.62276     20.187151
  284.61584     64.62435    115.73778     12.33445     91.38843
   30.54244     20.041323    12.954681   147.84776    116.4441
   51.080368    30.716064   699.18506     44.312286   159.72353
   91.40819    105.62128     32.259453   774.5375       8.798053
  121.26621     35.932106   117.752686    61.92397     19.686441
   18.177195     9.416929   185.58798    126.620415   124.5698
  235.43262    242.62157    243.03703     56.29961     33.313446
    8.019759    98.12543    109.560036    85.60593    120.14335
    8.647309    21.177217   208.48143    199.00618    148.12428
   16.671667    13.284448    15.80182      6.809344    80.39227
  266.01068    105.74406     74.31357     76.80385     35.901398
   41.089954   283.34402     33.436768   112.29904     23.223497
   22.542133    24.728216    80.833015   226.42744    165.29106
  100.473114   139.74289    141.02977     78.27254    111.22345
  117.39851     79.795815     4.4806557   13.679824    55.949528
   98.74188    430.5787      16.307703    13.749987     7.253408
   54.42134     29.53639     14.274477    30.44826     25.30872
   25.56054     79.97268     15.405342   316.99527     22.211637
   74.15112     26.721182    16.295898   299.28204    467.21262
  115.20912    159.58029      8.382612   136.64706     36.031807
  104.97125     12.787274    36.641422    44.289745    17.783379
   53.94842     95.89376      4.743683    22.916876    23.147438
   28.305813   208.727      189.36707     28.032938    19.172958
   66.76288     23.079966    25.088198    19.981901    24.688395
   71.67556    130.28615     10.202324    24.175776    94.627785
   19.246084    31.585724    11.6748      27.20835     29.143158
   76.8609      94.179924    40.713234   164.13911    141.42181
   10.218367    18.800417    48.55202    102.094696    13.96663
    8.359957    75.93522    540.50696    145.44847     58.77788
   20.856375     5.402184    56.28951     16.630808   330.74707
   95.47414     21.428       11.677934   116.354866    42.71887
  436.74954      8.037      156.1274      61.561333    84.76455
   49.43633     20.65097    100.68515     58.97964     60.010307
   59.070206    77.16157     75.75873     69.663       28.16393
    9.421977    11.363221   360.87418     14.438886   244.23224
  100.25321    273.8605      50.367046    11.051792    38.685806
   67.78994    103.64012     21.14647     10.619654   162.59686
   15.663558    68.38207     45.680977    13.399101    95.842545
   17.884687    71.67234      7.5646405  116.13536      5.2302756
  151.16925    299.49762     12.488031    16.969606    65.98593
  142.95493    197.7265     222.595       33.10157     14.583143
    7.0018573   11.355143    27.605072   247.01979     90.214714
   61.255154    93.20724     17.646408    91.1052      11.27628
   30.787992   216.14429     71.61595     49.19047     51.125443
   19.711088    21.06029      8.570395    68.14234     13.879814
  120.09426     66.51278    301.86        74.441345    20.5065
   18.346352    33.542927   117.00699     11.24167    138.247
  115.1306      33.5994     474.925       27.347324    19.373924
  304.7232      11.439525    40.16685     45.30025     26.675093
   71.71435     34.176403    86.197426    57.044518    97.24645
   67.33647     14.341154    79.332306    11.947616   785.71344
  117.32769     22.992       86.52892     45.028385   186.52077
  171.48956    194.48201     86.74603    341.15363    690.5874
    5.544939    74.2813      60.063576   336.49725      5.9482956
  179.50171    702.2221     251.77211    142.52945     40.91329
  233.20839     78.50826    103.1482     248.9333      15.087106
  267.85226     36.930344   172.95276     46.807713     8.607938
   34.39784    164.28528     34.993526    10.998723   289.21954
   23.301325    19.634838   127.75305     16.725649     9.8588915
  153.39413    106.18224    114.77579     26.44151    788.76587
   83.40047     31.211836   622.71985     55.32439     24.099873
    8.185336    79.09036     49.53289    180.8768      21.116146
  107.919495    16.7599      56.12433    129.06859      9.02989
  262.70654    124.51426    128.31218     99.626915    54.011333
  164.52017     18.057167    18.381166     6.692       38.063416
 1126.2585      75.757835    26.362      244.71567     48.15775
   15.596833   168.8267      29.708916   728.02344    128.5031
    7.639654   208.61597     10.813037   121.804825   350.99655
   97.726204    19.255121    15.876336     5.3418784  162.84415
  100.09346     33.507       13.066066    11.056374    76.75663
  110.4204      26.737556    14.792858     9.884293    12.538104
   41.49416     24.55803     87.28072     76.501884   212.14645
    9.650828    22.725172    69.657684   200.35132     78.1116
   75.47383     14.9719715  176.44705    116.26457    105.3948
   43.100914   209.72324     10.952143     5.4988284   36.306347
   73.0054     300.22632     80.67617     15.93225     71.72048
  133.39886    273.59317     43.99321     24.001268     8.582592
   26.468475   102.59676     82.24244    136.74844    103.713295
  262.2558     271.20154    106.160416    38.593224    61.929176
   14.255388    11.525735    95.71853     56.12409      9.942617
   35.172176     6.2244706   91.86794     81.1133     108.04536
   96.334854   214.51535     93.48706    370.98706     10.644149
  146.91795     58.138397    23.425663   141.11082    157.73293
   18.03395     50.95978     98.34558    143.4388      66.42288
  176.88663     74.99466     21.63078     49.67424    138.3687
   40.29066    249.14445     35.16073    728.0223      14.916636
   59.514454    27.484       14.823      193.49873     13.0914545
   64.45591     61.869274   286.36972     60.114635   325.60532
  173.90443     15.284388    34.93653    100.68364      4.664847
  427.03192      8.056469    54.650204    16.742228   282.1101
  137.59572     33.393898   179.40489    118.25044    128.03177
   14.124562   188.65941     52.902374   118.261406    26.637562
   10.407469    83.19169     64.11947     13.158093    75.49446
    6.370863   134.24655     77.05203      6.839526   300.4108
  147.7135      24.65081     54.859547   556.92737     92.53383
  157.96136    110.71942    105.78458     23.30441    145.62929
  154.26335     80.66451     16.719128   160.82846     80.96208
   50.82635    110.30965     90.521805    75.55136    152.94542
    5.848085    41.62481     37.69296    332.31494     30.895548
  116.89887     20.805775    62.74326     17.17413     61.080193
  193.58554     33.239902   154.34662     57.529644   163.81277
   23.958967    23.294544   118.37935    136.91397     30.042294
   80.88261     15.7028475  345.5821     135.75356    146.38255
  261.5444      27.52601    103.35424      8.433692   212.66534
  177.2466     136.90187    127.553535     9.3634615  342.84253
   17.398384   153.78221     79.44023     55.485397   350.9922
   63.4542     507.6457      24.6629      81.9966     221.3292
   98.8533     204.4977       5.7945     180.1818      19.241
  201.241      209.6775      98.814       85.7879     732.1047
  137.7093      40.3046      34.1901      50.2922     145.1268
   53.6129     126.31884     24.945776   117.05036    154.3686
  132.38545    402.66434     35.53564     91.13936    122.42073
  240.91028     11.755416    83.92255     60.268806    13.61925
   63.04582     48.494762    57.24041     12.191011   531.1069
  222.73088    230.81175     10.67942    313.94098     15.876307
    7.157966    24.451977   191.53452     36.566284   459.91873
  265.23932     84.843414    73.54252    105.866486   332.35562
   17.977345    57.510933    25.989723   464.9764     102.50669
   82.09748     71.022514   320.07776     87.012314    22.795862
   48.55563     19.153465     7.9930463   48.84028     92.25011
   87.242966   235.21239     24.829535    56.971466    40.70323
   18.116686    83.31729     12.4332905  139.04675    201.2604
  114.22821    315.5243      48.210884    18.972635    62.88861
  248.01692    388.60876    167.60648   1001.7247      34.89565
   12.573635    30.851152   197.22197     15.818824    12.700059
  236.98196     54.281963   199.13474     71.12775    171.77528
  102.657646   732.69696     56.899178    64.55593     34.987286
   18.906643   575.0038      52.247463    97.84403     76.99586
   74.755196    71.85091     63.507793   158.74493     71.76329
  113.233665    70.08799    412.37665     26.141314     9.765
  180.03275     15.791964     9.953133    94.63825    412.55035
   24.281784    10.60894     79.75328      5.925951   155.64304
  113.74057    199.37009    150.5284      72.02788    164.53427
  130.82872    138.97734    122.028694     4.0209146  131.44017
   49.78833    237.14671     23.60294    404.063       43.936222
  303.25388     25.737112   168.35844    144.92644    773.0211
   77.858       68.97522     92.76833     23.849667    62.41811
  167.93        64.51278     32.65867     66.721      401.85956
  131.59511      9.246333    40.04289     55.271      182.095
   11.914556   418.86432    260.58276    135.19733      1.9096667
   71.906624    36.8829      31.275       72.17089     50.973186
  203.94528     44.60344     53.5338       8.60715    117.6561
   80.75745      9.136687   146.94435    257.15576    304.51163
   88.674866    86.66933     65.337975   187.08772     77.97678
   88.55761     24.334633    25.098152   138.00304    153.47267
   80.92538     87.70739      9.785962    34.168102   244.35968
   58.824455   120.139175    15.690304    14.071443     9.133975
  203.36354     18.63843     27.880177   451.3057      89.36647
    4.984177    18.235846    40.608       95.955345   103.808075
   92.463234   162.1762     112.24731    263.3639      16.696154
   86.61796      9.991615    15.155192   493.06882    107.909424
  119.76658    137.27931     87.13087      9.741974   225.7124
   11.812792    26.995792    27.692299    15.254533     7.4714026
  146.57785     19.522987   167.36096     15.273       71.39314
    7.2113376  176.59227     42.800495   114.1373     259.4097
  148.07922    227.76862    185.82573    134.1861      35.356617
   34.81792     81.15217    314.93973    116.620224    43.456264
    5.816842    16.869198   153.25247     78.28437    211.51729
  831.02765     75.43871     85.2705     177.31906     17.93404
  151.74367    181.75597    126.75288     39.96912     68.04828
    7.99128     96.29712     66.53592     39.24732    137.148    ]
Feature: Items_per_trx
Tensor: [ 6.  4.  2.  5.  3. 16.  9. 12. 14.  8.  7. 11. 10. 21. 18. 15. 13. 19.
 20. 17. 29.]
Feature: Unique_items_per_trx
Tensor: [ 2.  1.  3.  4.  5.  6.  9.  7.  8. 11. 10.]
In [56]:
class SimilarityLayer(tf.keras.layers.Layer):
    def __init__(self, embedding_dim, temperature=1.0, **kwargs):
        super(SimilarityLayer, self).__init__(**kwargs)
        self.temperature = temperature
        # Define projection layers
        self.member_projection = tf.keras.layers.Dense(embedding_dim, activation='relu')
        self.item_projection = tf.keras.layers.Dense(embedding_dim, activation='relu')

    def call(self, member_embeddings, item_embeddings):
        # Ensure both tensors have the same data type
        dtype = tf.float32
        member_embeddings = tf.cast(member_embeddings, dtype)
        item_embeddings = tf.cast(item_embeddings, dtype)
        
        # Project embeddings to the same dimension
        member_embeddings = self.member_projection(member_embeddings)
        item_embeddings = self.item_projection(item_embeddings)
        
        # Normalize the embeddings
        member_embeddings = tf.nn.l2_normalize(member_embeddings, axis=-1)
        item_embeddings = tf.nn.l2_normalize(item_embeddings, axis=-1)
        
        # Compute the similarity as the dot product
        similarity = tf.matmul(member_embeddings, item_embeddings, transpose_b=True)
        
        # Scale the similarity by temperature
        similarity = similarity / self.temperature
        
        # Return both the similarity and the projected embeddings
        return similarity, member_embeddings, item_embeddings
In [57]:
class RetrievalModelWithTopK(tfrs.Model):
    def __init__(self, member_model, item_model, similarity_model, k=10):
        super().__init__()
        self.member_model = member_model
        self.item_model = item_model
        self.similarity_model = similarity_model
        self.k = 10
        
        # Initialize the FactorizedTopK retrieval layer
        self.top_k = tfrs.layers.factorized_top_k.BruteForce()

    def retrieve_top_k(self, member_features, item_features):
        # Get embeddings from the models
        member_embeddings = self.member_model(member_features)
        item_embeddings = self.item_model(item_features)

        # Get similarity and projected embeddings from SimilarityLayer
        similarity, projected_member_embeddings, projected_item_embeddings = self.similarity_model(member_embeddings, item_embeddings)

        # Index the item embeddings with the retrieval layer using the projected embeddings
        self.top_k.index(projected_item_embeddings)

        # Get top-k items for the given member features using the projected embeddings
        top_k_values, top_k_indices = self.top_k(projected_member_embeddings)

        return top_k_values, top_k_indices

    def compute_loss(self, member_features, item_features, training=False):
        top_k_values, top_k_indices = self.retrieve_top_k(member_features, item_features)
        # Further processing...
        return top_k_values, top_k_indices
In [58]:
Similarity_model = SimilarityLayer(temperature=1, embedding_dim=64)
retrieval_model = RetrievalModelWithTopK(member_model,item_model,Similarity_model,k=10)
In [59]:
top_k_scores, top_k_indices = retrieval_model.compute_loss(member_features, item_features)

# Convert tensors to numpy arrays for easier reading
top_k_scores_np = top_k_scores.numpy()
top_k_indices_np = top_k_indices.numpy()

# Print the shape of the results
print("Top-k Scores Shape:", top_k_scores_np.shape)
print("Top-k Indices Shape:", top_k_indices_np.shape)
Shape of member_embeddings: (1000, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (before padding): (140, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (before padding): (160, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (before padding): (150, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (before padding): (152, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (before padding): (143, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (before padding): (168, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (before padding): (169, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (before padding): (166, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (before padding): (154, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (before padding): (147, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (before padding): (177, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (before padding): (185, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (before padding): (136, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (before padding): (163, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (before padding): (182, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (before padding): (180, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (before padding): (402, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (before padding): (531, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (before padding): (561, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (before padding): (583, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (before padding): (401, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (before padding): (523, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (before padding): (560, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (before padding): (602, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (before padding): (366, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (before padding): (457, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (before padding): (515, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (before padding): (541, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (before padding): (585, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (before padding): (352, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (before padding): (432, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (before padding): (495, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (before padding): (535, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (before padding): (558, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of Total_spend normalized_values (before padding): (999,)
Shape of Total_spend normalized_values (after padding): (1000,)
Shape of Total_trx normalized_values (before padding): (219,)
Shape of Total_trx normalized_values (after padding): (1000,)
Shape of Total_item normalized_values (before padding): (680,)
Shape of Total_item normalized_values (after padding): (1000,)
Shape of Total_unique_items normalized_values (before padding): (453,)
Shape of Total_unique_items normalized_values (after padding): (1000,)
Shape of Total_unique_subclasses normalized_values (before padding): (231,)
Shape of Total_unique_subclasses normalized_values (after padding): (1000,)
Shape of Total_unique_subdepartments normalized_values (before padding): (79,)
Shape of Total_unique_subdepartments normalized_values (after padding): (1000,)
Shape of Min_spend normalized_values (before padding): (92,)
Shape of Min_spend normalized_values (after padding): (1000,)
Shape of Max_spend normalized_values (before padding): (681,)
Shape of Max_spend normalized_values (after padding): (1000,)
Shape of days_since_last_purchase normalized_values (before padding): (74,)
Shape of days_since_last_purchase normalized_values (after padding): (1000,)
Shape of days_since_first_purchase normalized_values (before padding): (79,)
Shape of days_since_first_purchase normalized_values (after padding): (1000,)
Shape of spend_per_trx normalized_values (before padding): (1000,)
Shape of Items_per_trx normalized_values (before padding): (21,)
Shape of Items_per_trx normalized_values (after padding): (1000,)
Shape of Unique_items_per_trx normalized_values (before padding): (11,)
Shape of Unique_items_per_trx normalized_values (after padding): (1000,)
Shape of final_concatenated_tensor: (1000, 136)
Shape of Item_embeddings: (34663, 3)
Shape of Item_subclass feature_embeddings (before padding): (1374, 3)
Shape of Item_subclass feature_embeddings (after padding): (34663, 3)
Shape of Item_subdepartment feature_embeddings (before padding): (220, 3)
Shape of Item_subdepartment feature_embeddings (after padding): (34663, 3)
Shape of Total_price_7_days normalized_values (before padding): (4776,)
Shape of Total_price_7_days normalized_values (after padding): (34663,)
Shape of Itm_qty_7_days normalized_values (before padding): (272,)
Shape of Itm_qty_7_days normalized_values (after padding): (34663,)
Shape of Trx_count_7_days normalized_values (before padding): (217,)
Shape of Trx_count_7_days normalized_values (after padding): (34663,)
Shape of Total_price_15_days normalized_values (before padding): (7245,)
Shape of Total_price_15_days normalized_values (after padding): (34663,)
Shape of Itm_qty_15_days normalized_values (before padding): (434,)
Shape of Itm_qty_15_days normalized_values (after padding): (34663,)
Shape of Trx_count_15_days normalized_values (before padding): (346,)
Shape of Trx_count_15_days normalized_values (after padding): (34663,)
Shape of Total_price_60_days normalized_values (before padding): (13710,)
Shape of Total_price_60_days normalized_values (after padding): (34663,)
Shape of Itm_qty_60_days normalized_values (before padding): (951,)
Shape of Itm_qty_60_days normalized_values (after padding): (34663,)
Shape of Trx_count_60_days normalized_values (before padding): (738,)
Shape of Trx_count_60_days normalized_values (after padding): (34663,)
Shape of Total_price_90_days normalized_values (before padding): (16172,)
Shape of Total_price_90_days normalized_values (after padding): (34663,)
Shape of Itm_qty_90_days normalized_values (before padding): (1193,)
Shape of Itm_qty_90_days normalized_values (after padding): (34663,)
Shape of Trx_count_90_days normalized_values (before padding): (947,)
Shape of Trx_count_90_days normalized_values (after padding): (34663,)
Shape of final_concatenated_tensor: (34663, 21)
Top-k Scores Shape: (1000, 10)
Top-k Indices Shape: (1000, 10)
In [60]:
all_scores = tf.concat([tf.reshape(top_k_scores[m], [-1]) for m in range(top_k_scores.shape[0])], axis=0)
all_scores = all_scores.numpy()  # Convert tensor to numpy array for analysis

import matplotlib.pyplot as plt

# Increase figure size
fig, ax = plt.subplots(figsize=(12, 6))  # Adjust width and height as needed

# Create the histogram
counts, bins, patches = ax.hist(all_scores, bins=50, edgecolor='black', linewidth=0.5, histtype='bar')

# Adjust bar width and thickness
for patch in patches:
    patch.set_edgecolor('black')  # Set edge color
    patch.set_linewidth(1.5)      # Thicker bar edges
    # Optionally adjust the width here if needed

# Add data labels on top of each bar
for count, bin, patch in zip(counts, bins, patches):
    # Calculate the height of the label
    height = patch.get_height()
    # Add the label with size 7 and color black
    ax.text(patch.get_x() + patch.get_width() / 2, height, f'{int(count)}', 
            ha='center', va='bottom', fontsize=7, color='black')

# Customize the plot
ax.set_title('Distribution of Similarity Scores')
ax.set_xlabel('Score')
ax.set_ylabel('Frequency')

# Adjust layout for better spacing
plt.tight_layout()

# Show the plot
plt.show()
In [61]:
import tensorflow as tf

class RankingModel(tf.keras.Model):
    def __init__(self, embedding_dim, **kwargs):
        super(RankingModel, self).__init__(**kwargs)
        # Define dense layers for the ranking model
        self.dense1 = tf.keras.layers.Dense(128, activation='relu')
        self.dense2 = tf.keras.layers.Dense(64, activation='relu')
        self.dense3 = tf.keras.layers.Dense(1)  # Output layer for ranking score

    def call(self, member_embeddings, item_embeddings):
        # Concatenate member and item embeddings
        combined_embeddings = tf.concat([member_embeddings, item_embeddings], axis=-1)
        
        # Pass through dense layers
        x = self.dense1(combined_embeddings)
        x = self.dense2(x)
        ranking_scores = self.dense3(x)
        
        return ranking_scores
In [62]:
import tensorflow as tf
import tensorflow_recommenders as tfrs

class RankingRetrievalModel(tfrs.Model):
    def __init__(self, member_model, item_model, similarity_model, ranking_model, k=10):
        super().__init__()
        self.member_model = member_model
        self.item_model = item_model
        self.similarity_model = similarity_model
        self.ranking_model = ranking_model
        self.k = k
        
        # Initialize the BruteForce retrieval layer
        self.top_k = tfrs.layers.factorized_top_k.BruteForce()

    def retrieve_top_k(self, member_features, item_features):
        # Get embeddings from the models
        member_embeddings = self.member_model(member_features)
        item_embeddings = self.item_model(item_features)

        # Get similarity and projected embeddings from SimilarityLayer
        similarity, projected_member_embeddings, projected_item_embeddings = self.similarity_model(member_embeddings, item_embeddings)

        # Debug: Print shapes
        print(f"Projected member embeddings shape: {projected_member_embeddings.shape}")
        print(f"Projected item embeddings shape: {projected_item_embeddings.shape}")

        # Index the item embeddings with the retrieval layer using the projected embeddings
        self.top_k.index(projected_item_embeddings)

        # Get top-k items for the given member features using the projected embeddings
        top_k_values, top_k_indices = self.top_k(projected_member_embeddings)

        return top_k_values, top_k_indices

    def compute_loss(self, member_features, item_features, training=False):
        top_k_values, top_k_indices = self.retrieve_top_k(member_features, item_features)
        return top_k_values, top_k_indices
In [63]:
similarity_model = SimilarityLayer(embedding_dim=32, temperature=1.0)  
ranking_model = tf.keras.Sequential([
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)
])  # Example ranking model

# Create an instance of the RankingRetrievalModel
ranking_retrieval_model = RankingRetrievalModel(
    member_model=member_model,
    item_model=item_model,
    similarity_model=similarity_model,
    ranking_model=ranking_model,
    k=10  # Number of top items to retrieve
)
In [64]:
top_k_values, top_k_indices = ranking_retrieval_model.retrieve_top_k(member_features, item_features)
Shape of member_embeddings: (1000, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (before padding): (140, 3)
Shape of top_1_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (before padding): (160, 3)
Shape of top_3_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (before padding): (150, 3)
Shape of top_4_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (before padding): (152, 3)
Shape of top_5_7_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (before padding): (143, 3)
Shape of top_1_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (before padding): (168, 3)
Shape of top_2_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (before padding): (169, 3)
Shape of top_3_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (before padding): (166, 3)
Shape of top_4_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (before padding): (154, 3)
Shape of top_5_15_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (before padding): (147, 3)
Shape of top_1_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (before padding): (170, 3)
Shape of top_2_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (before padding): (177, 3)
Shape of top_3_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_4_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (before padding): (185, 3)
Shape of top_5_60_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (before padding): (136, 3)
Shape of top_1_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (before padding): (174, 3)
Shape of top_2_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (before padding): (163, 3)
Shape of top_3_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (before padding): (182, 3)
Shape of top_4_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (before padding): (180, 3)
Shape of top_5_90_day_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (before padding): (402, 3)
Shape of top_1_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (before padding): (531, 3)
Shape of top_3_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (before padding): (561, 3)
Shape of top_4_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (before padding): (583, 3)
Shape of top_5_7_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (before padding): (401, 3)
Shape of top_1_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (before padding): (487, 3)
Shape of top_2_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (before padding): (523, 3)
Shape of top_3_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (before padding): (560, 3)
Shape of top_4_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (before padding): (602, 3)
Shape of top_5_15_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (before padding): (366, 3)
Shape of top_1_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (before padding): (457, 3)
Shape of top_2_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (before padding): (515, 3)
Shape of top_3_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (before padding): (541, 3)
Shape of top_4_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (before padding): (585, 3)
Shape of top_5_60_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (before padding): (352, 3)
Shape of top_1_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (before padding): (432, 3)
Shape of top_2_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (before padding): (495, 3)
Shape of top_3_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (before padding): (535, 3)
Shape of top_4_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (before padding): (558, 3)
Shape of top_5_90_day_non_fresh_product feature_embeddings (after padding): (1000, 3)
Shape of Total_spend normalized_values (before padding): (999,)
Shape of Total_spend normalized_values (after padding): (1000,)
Shape of Total_trx normalized_values (before padding): (219,)
Shape of Total_trx normalized_values (after padding): (1000,)
Shape of Total_item normalized_values (before padding): (680,)
Shape of Total_item normalized_values (after padding): (1000,)
Shape of Total_unique_items normalized_values (before padding): (453,)
Shape of Total_unique_items normalized_values (after padding): (1000,)
Shape of Total_unique_subclasses normalized_values (before padding): (231,)
Shape of Total_unique_subclasses normalized_values (after padding): (1000,)
Shape of Total_unique_subdepartments normalized_values (before padding): (79,)
Shape of Total_unique_subdepartments normalized_values (after padding): (1000,)
Shape of Min_spend normalized_values (before padding): (92,)
Shape of Min_spend normalized_values (after padding): (1000,)
Shape of Max_spend normalized_values (before padding): (681,)
Shape of Max_spend normalized_values (after padding): (1000,)
Shape of days_since_last_purchase normalized_values (before padding): (74,)
Shape of days_since_last_purchase normalized_values (after padding): (1000,)
Shape of days_since_first_purchase normalized_values (before padding): (79,)
Shape of days_since_first_purchase normalized_values (after padding): (1000,)
Shape of spend_per_trx normalized_values (before padding): (1000,)
Shape of Items_per_trx normalized_values (before padding): (21,)
Shape of Items_per_trx normalized_values (after padding): (1000,)
Shape of Unique_items_per_trx normalized_values (before padding): (11,)
Shape of Unique_items_per_trx normalized_values (after padding): (1000,)
Shape of final_concatenated_tensor: (1000, 136)
Shape of Item_embeddings: (34663, 3)
Shape of Item_subclass feature_embeddings (before padding): (1374, 3)
Shape of Item_subclass feature_embeddings (after padding): (34663, 3)
Shape of Item_subdepartment feature_embeddings (before padding): (220, 3)
Shape of Item_subdepartment feature_embeddings (after padding): (34663, 3)
Shape of Total_price_7_days normalized_values (before padding): (4776,)
Shape of Total_price_7_days normalized_values (after padding): (34663,)
Shape of Itm_qty_7_days normalized_values (before padding): (272,)
Shape of Itm_qty_7_days normalized_values (after padding): (34663,)
Shape of Trx_count_7_days normalized_values (before padding): (217,)
Shape of Trx_count_7_days normalized_values (after padding): (34663,)
Shape of Total_price_15_days normalized_values (before padding): (7245,)
Shape of Total_price_15_days normalized_values (after padding): (34663,)
Shape of Itm_qty_15_days normalized_values (before padding): (434,)
Shape of Itm_qty_15_days normalized_values (after padding): (34663,)
Shape of Trx_count_15_days normalized_values (before padding): (346,)
Shape of Trx_count_15_days normalized_values (after padding): (34663,)
Shape of Total_price_60_days normalized_values (before padding): (13710,)
Shape of Total_price_60_days normalized_values (after padding): (34663,)
Shape of Itm_qty_60_days normalized_values (before padding): (951,)
Shape of Itm_qty_60_days normalized_values (after padding): (34663,)
Shape of Trx_count_60_days normalized_values (before padding): (738,)
Shape of Trx_count_60_days normalized_values (after padding): (34663,)
Shape of Total_price_90_days normalized_values (before padding): (16172,)
Shape of Total_price_90_days normalized_values (after padding): (34663,)
Shape of Itm_qty_90_days normalized_values (before padding): (1193,)
Shape of Itm_qty_90_days normalized_values (after padding): (34663,)
Shape of Trx_count_90_days normalized_values (before padding): (947,)
Shape of Trx_count_90_days normalized_values (after padding): (34663,)
Shape of final_concatenated_tensor: (34663, 21)
Projected member embeddings shape: (1000, 32)
Projected item embeddings shape: (34663, 32)
In [65]:
all_scores = tf.concat([tf.reshape(top_k_values[m], [-1]) for m in range(top_k_values.shape[0])], axis=0)
all_scores = all_scores.numpy()  # Convert tensor to numpy array for analysis

import matplotlib.pyplot as plt

# Increase figure size
fig, ax = plt.subplots(figsize=(12, 6))  # Adjust width and height as needed

# Create the histogram
counts, bins, patches = ax.hist(all_scores, bins=50, edgecolor='black', linewidth=0.5, histtype='bar')

# Adjust bar width and thickness
for patch in patches:
    patch.set_edgecolor('black')  # Set edge color
    patch.set_linewidth(1.5)      # Thicker bar edges
    # Optionally adjust the width here if needed

# Add data labels on top of each bar
for count, bin, patch in zip(counts, bins, patches):
    # Calculate the height of the label
    height = patch.get_height()
    # Add the label with size 7 and color black
    ax.text(patch.get_x() + patch.get_width() / 2, height, f'{int(count)}', 
            ha='center', va='bottom', fontsize=7, color='black')

# Customize the plot
ax.set_title('Distribution of Similarity Scores')
ax.set_xlabel('Score')
ax.set_ylabel('Frequency')

# Adjust layout for better spacing
plt.tight_layout()

# Show the plot
plt.show()
In [66]:
member_ids = member_features_df['Member_id'].values
item_ids = Item_features_df['Item_id'].values
In [67]:
# for i, (scores, indices) in enumerate(zip(top_k_values, top_k_indices)):
#     member_id = member_ids[i]  # Get the member ID for this iteration
#     print(f"Member ID: {member_id}")

#     # Map top-k indices to item IDs
#     top_k_item_ids = item_ids[indices.numpy()]
#     print(f"Top-k Item IDs: {top_k_item_ids}")
#     print(f"Top-k Scores: {scores.numpy()}")
In [68]:
# Initialize an empty list to store the rows
rows = []

member_ids = member_features_df['Member_id'].values
# Extract unique Item_id and Item_name pairs
unique_item_names_df = df.drop_duplicates(subset=['Item_id', 'Item_name'])

# Create a mapping of Item_id to Item_name
item_id_to_name_mapping = dict(zip(unique_item_names_df['Item_id'], unique_item_names_df['Item_name']))

member_ids = member_features_df['Member_id'].values

for i, (scores, indices) in enumerate(zip(top_k_values, top_k_indices)):
    member_id = member_ids[i]  # Get the member ID for this iteration

    # Map top-k indices to item IDs
    top_k_item_ids = item_ids[indices]
    
    # Map item IDs to item names using the mapping
    top_k_item_names = [item_id_to_name_mapping[item_id] for item_id in top_k_item_ids]
    
    # Create rows for the DataFrame
    for item_id, item_name, score in zip(top_k_item_ids, top_k_item_names, scores):
        score_value = score.numpy()
        rows.append({
            'Member_id': member_id,
            'Item_id': item_id,
            'Item_name': item_name,
            'Score': score_value
        })

# Create the DataFrame
top_k_df = pd.DataFrame(rows)
In [69]:
pd.set_option('display.max_rows',None)
top_k_df.head(5)
Out[69]:
Member_id Item_id Item_name Score
0 124334 9140 Halawani Bros Plain Beef Mortadella /kg 0.644868
1 124334 7508 Almarai Double Chocolate Milk 18*200 ml 0.627167
2 124334 2168 Clorox Clothes Original Stain Remover 1.8 L 0.609057
3 124334 9560 Golden Chicken Fresh Chicken Liver 400 g 0.608852
4 124334 8428 Americana Twisterz Mini Chicken Strips 750g 0.607189
In [70]:
top_k_df.to_csv('Recommendations_top_10.csv')
In [71]:
unique_item_id_df = df.drop_duplicates(subset=['Item_id'])
In [ ]:
 
In [72]:
# Assuming you have `item_features_df` and `df2` with `item_subclass`

# Map item_ids to their item_subclass
item_subclass_map = Item_features_df.set_index('Item_id')['Item_subclass'].to_dict()

# Function to get item_subclass for a list of item_ids
def get_item_subclasses(item_ids):
    return [item_subclass_map.get(item_id, 'Unknown') for item_id in item_ids]
In [73]:
import pandas as pd

# Sample DataFrames
# top_k_df contains columns Member_id, Item_id, Item_name, Score
# df contains columns Member_id, Item_id, Item_subclass

# Create a mapping from item_id to item_subclass
item_subclass_map = Item_features_df.set_index('Item_id')['Item_subclass'].to_dict()

# Create a mapping from item_id to item_subclass in transactional data
true_item_subclasses = df[['Item_id', 'Item_subclass']].drop_duplicates().set_index('Item_id')['Item_subclass'].to_dict()

# Function to get item_subclass for a list of item_ids
def get_item_subclasses(item_ids):
    return [item_subclass_map.get(item_id, 'Unknown') for item_id in item_ids]

# Function to evaluate the top-K recommendations for each member
def evaluate_member_recommendations(member_id, top_k_df, k):
    # Get the item_ids from transactions for this member
    member_transactions = df[df['Member_id'] == member_id]
    true_item_ids = member_transactions['Item_id'].unique()
    
    # Get item_subclasses for true item_ids
    true_item_subclasses_for_member = set(true_item_subclasses.get(item_id, 'Unknown') for item_id in true_item_ids)
    
    # Filter the top-k items for this member
    member_recommendations = top_k_df[top_k_df['Member_id'] == member_id]
    top_k_items = member_recommendations.head(k)
    
    # Get item_subclasses for top-K recommended items
    top_k_subclasses = set(top_k_df[top_k_df['Item_id'].isin(top_k_items['Item_id'])]['Item_id'].map(lambda x: item_subclass_map.get(x, 'Unknown')))
    
    # Evaluate Precision, Recall, and Accuracy
    hits = true_item_subclasses_for_member.intersection(top_k_subclasses)
    
    precision = len(hits) / k if k > 0 else 0
    recall = len(hits) / len(true_item_subclasses_for_member) if true_item_subclasses_for_member else 0
    accuracy = 1 if len(hits) > 0 else 0

    return accuracy, precision, recall

# Evaluate recommendations for each member in the DataFrame
results = []
k = 5  # Define the value of K
for member_id in top_k_df['Member_id'].unique():
    accuracy, precision, recall = evaluate_member_recommendations(member_id, top_k_df, k)
    results.append({'Member_id': member_id, 'Accuracy': accuracy, 'Precision': precision, 'Recall': recall})

# Convert results to DataFrame for better readability
results_df = pd.DataFrame(results)
results_df.head()
Out[73]:
Member_id Accuracy Precision Recall
0 124334 1 0.8 0.016949
1 6765190 1 0.4 0.017241
2 12 1 0.6 0.029703
3 3902052 1 0.6 0.038462
4 168740 1 0.6 0.015000
In [74]:
results_df.to_csv('Results_top_10.csv')
In [75]:
overall_accuracy = results_df['Accuracy'].mean()
overall_precision = results_df['Precision'].mean()
overall_recall = results_df['Recall'].mean()

print("Overall Accuracy: {:.4f}".format(overall_accuracy))
print("Overall Precision: {:.4f}".format(overall_precision))
print("Overall Recall: {:.4f}".format(overall_recall))
Overall Accuracy: 0.8580
Overall Precision: 0.3644
Overall Recall: 0.0178
In [76]:
from sklearn.metrics import f1_score

def f1_score_at_k(true_labels, recommendations, k):
    y_true = [1 if item in true_labels[i] else 0 for i in range(len(recommendations)) for item in recommendations[i][:k]]
    y_pred = [1] * len(y_true)  # All predictions are relevant items

    return f1_score(y_true, y_pred)

# Convert top_k_df to a list of recommendations for each user
recommendations = top_k_df.groupby('Member_id')['Item_id'].apply(list).tolist()

# Create a dictionary of true relevant items for each user
true_relevant_items = df.groupby('Member_id')['Item_id'].apply(set).to_dict()

# Calculate F1 Score
true_labels = [true_relevant_items.get(member_id, set()) for member_id in top_k_df['Member_id'].unique()]
f1_score_value = f1_score_at_k(true_labels, recommendations, k=10)
print(f'F1 Score at K: {f1_score_value}')
F1 Score at K: 0.058252427184466014
In [77]:
def hit_rate(true_labels, recommendations):
    hits = [1 if any(item in true_labels[i] for item in recommendations[i]) else 0 for i in range(len(recommendations))]
    return sum(hits) / len(hits)

# Convert top_k_df to a list of recommendations for each user
recommendations = top_k_df.groupby('Member_id')['Item_id'].apply(list).tolist()

# Create a dictionary of true relevant items for each user
true_relevant_items = df.groupby('Member_id')['Item_id'].apply(set).to_dict()

# Calculate Hit Rate
true_labels = [true_relevant_items.get(member_id, set()) for member_id in top_k_df['Member_id'].unique()]
hit_rate_value = hit_rate(true_labels, recommendations)
print(f'Hit Rate: {hit_rate_value}')
Hit Rate: 0.245
In [ ]:
def hit_rate(true_labels, recommendations):
    hits = [1 if any(item in true_labels[i] for item in recommendations[i]) else 0 for i in range(len(recommendations))]
    return sum(hits) / len(hits)

# Convert top_k_df to a list of recommendations for each user
recommendations = top_k_df.groupby('Member_id')['Item_id'].apply(list).tolist()

# Create a dictionary of true relevant items for each user
true_relevant_items = df.groupby('Member_id')['Item_id'].apply(set).to_dict()

# Calculate Hit Rate
true_labels = [true_relevant_items.get(member_id, set()) for member_id in top_k_df['Member_id'].unique()]
hit_rate_value = hit_rate(true_labels, recommendations)
print(f'Hit Rate: {hit_rate_value}')
In [ ]:
def hit_rate(true_labels, recommendations):
    hits = [1 if any(item in true_labels[i] for item in recommendations[i]) else 0 for i in range(len(recommendations))]
    return sum(hits) / len(hits)

# Convert top_k_df to a list of recommendations for each user
recommendations = top_k_df.groupby('Member_id')['Item_id'].apply(list).tolist()

# Create a dictionary of true relevant items for each user
true_relevant_items = df.groupby('Member_id')['Item_id'].apply(set).to_dict()

# Calculate Hit Rate
true_labels = [true_relevant_items.get(member_id, set()) for member_id in top_k_df['Member_id'].unique()]
hit_rate_value = hit_rate(true_labels, recommendations)
print(f'Hit Rate: {hit_rate_value}')
In [ ]:
 
In [ ]:
def hit_rate(true_labels, recommendations):
    hits = [1 if any(item in true_labels[i] for item in recommendations[i]) else 0 for i in range(len(recommendations))]
    return sum(hits) / len(hits)

# Convert top_k_df to a list of recommendations for each user
recommendations = top_k_df.groupby('Member_id')['Item_id'].apply(list).tolist()

# Create a dictionary of true relevant items for each user
true_relevant_items = df.groupby('Member_id')['Item_id'].apply(set).to_dict()

# Calculate Hit Rate
true_labels = [true_relevant_items.get(member_id, set()) for member_id in top_k_df['Member_id'].unique()]
hit_rate_value = hit_rate(true_labels, recommendations)
print(f'Hit Rate: {hit_rate_value}')